# Text Generation Models, Page 18: Open-Weight AI Source: https://savrn.com/models/tasks/text-generation/page/18 Markdown alternate of the page above; the site index is https://savrn.com/llms.txt --- SAVRN Model Hub · Models by Task # Text Generation Models 1,582 open-weight text generation models in the SAVRN Model Hub, with Convergent Intelligence, Qwen and Francesca Padovani publishing the most. 1,582Models 732Publishers 107K to 1.7TParameter range 8Licenses ## SAVRN's Take Text generation is where most of the attention goes, and where most of the money is spent. The models on this page run from tiny research checkpoints that fit on a laptop to frontier-class systems that need a full server of accelerators. The first question we ask about any of them is not how smart it is, but what it costs to keep it answering around the clock. That cost comes down to three things: the size of the weights, the precision you run them at, and how much context each request carries. Moving from 16-bit to 4-bit cuts the memory a model needs by roughly four times, which is often the difference between one server and several. Mixture-of-experts models, such as the newer DeepSeek, Qwen and Nemotron releases, hold a large total parameter count but activate only a small share per token, so they answer faster than their size suggests while still needing the memory to hold every expert. Licensing decides the rest. Apache 2.0 and MIT models can go straight into a commercial product. Llama, Gemma's earlier generations and models marked other each carry terms you need to read first, and a model with no stated license is research material until the publisher says otherwise. Our advice is to shortlist by license, size to the hardware you can actually run, then test the survivors on your own prompts. The table below is sorted by what people download, not by what we recommend. SAVRN Research, 2026-09-18 ## Most Downloaded | Model | Publisher | Parameters | License | Monthly downloads | Cheapest GPUs at 16-bit | | --- | --- | --- | --- | --- | --- | | [Qwen3-0.6B](https://savrn.com/models/qwen3-0-6b) | Qwen | 752M | apache-2.0 | 25.2M | 1x MI300X, $1.85/hr | | [gpt2](https://savrn.com/models/gpt2) | OpenAI community | 137M | mit | 18.8M | 1x MI300X, $1.85/hr | | [Qwen3-4B](https://savrn.com/models/qwen3-4b) | Qwen | 4B | apache-2.0 | 11.4M | 1x MI300X, $1.85/hr | | [Qwen3-14B](https://savrn.com/models/qwen3-14b) | Qwen | 14.8B | apache-2.0 | 9.4M | 1x MI300X, $1.85/hr | | [Qwen3-8B](https://savrn.com/models/qwen3-8b) | Qwen | 8.2B | apache-2.0 | 8.1M | 1x MI300X, $1.85/hr | | [Qwen2.5-7B-Instruct](https://savrn.com/models/qwen2-5-7b-instruct) | Qwen | 7.6B | apache-2.0 | 6.4M | 1x MI300X, $1.85/hr | | [gpt-oss-20b](https://savrn.com/models/gpt-oss-20b) | OpenAI | 20.9B | apache-2.0 | 5.7M | 1x MI300X, $1.85/hr | | [opt-125m](https://savrn.com/models/opt-125m) | AI at Meta | — | other | 5.6M | — | | [DeepSeek-V3.2](https://savrn.com/models/deepseek-v3-2) | DeepSeek | 685.4B | mit | 5.4M | 7x MI325X, $14.00/hr | | [Qwen2.5-0.5B-Instruct](https://savrn.com/models/qwen2-5-0-5b-instruct) | Qwen | 494M | apache-2.0 | 5.3M | 1x MI300X, $1.85/hr | ## Licenses | License | Models | Commercial use | | --- | --- | --- | | [apache-2.0](https://savrn.com/models/licenses/apache-2-0) | 734 | Yes | | not stated | 345 | Not stated | | other | 175 | Read the license | | [mit](https://savrn.com/models/licenses/mit) | 152 | Yes | | [cc-by-nc-4.0](https://savrn.com/models/licenses/cc-by-nc-4-0) | 42 | Not without separate permission | | [llama3.2](https://savrn.com/models/licenses/llama3-2) | 33 | Read the license | | [gemma](https://savrn.com/models/licenses/gemma) | 22 | Yes, with conditions | | [llama3.1](https://savrn.com/models/licenses/llama3-1) | 21 | Yes, with conditions | ## Who Publishes Them | Publisher | Models | | --- | --- | | [Convergent Intelligence](https://savrn.com/model-publishers/reaperdoesntknow) | 54 | | [Qwen](https://savrn.com/model-publishers/qwen) | 42 | | [Francesca Padovani](https://savrn.com/model-publishers/francesca9805) | 37 | | [Yanggangu](https://savrn.com/model-publishers/yanggangu) | 28 | | [Shreyansh singh](https://savrn.com/model-publishers/shreyansh12183) | 25 | | [Kumar](https://savrn.com/model-publishers/sandeep123) | 23 | ## All 1,582 Models, Page 18 of 27 Model · Text generation ### [LLMPretrain](https://savrn.com/models/llmpretrain) [Dikshan Karwa](https://savrn.com/model-publishers/dikshan1234) Every weight in this model was produced by this project. There is no frompretrained, no base checkpoint, and no adapter: the tokenizer, the architecture code, the data pipeline and the training loop are all bespoke, and training started from a random initialisation. Trained on a single RTX 5070 Ti (16 GB). Written by hand — no transformers model classes were used to define it. 309,705,984 transformer blocks. Bits per byte is the headline metric. This model's vocabulary (32,768) differs from GPT-2's (50,257), and cross-entropy per token is not comparable across tokenizers. BPB divides that out and is directly comparable. Validation loss is measured on a held-out slice of the training corpus… Open weights cc-by-nc-4.0 transformers [View model](https://savrn.com/models/llmpretrain) Model · Text generation ### [LMLM_97M_1](https://savrn.com/models/lmlm-97m-1) [Sr Aivante](https://savrn.com/model-publishers/sraivante) A 97.6M-parameter language model trained from scratch, then fine-tuned for short, polite, everyday English conversation. It is a small, open research and learning model: you can read every line of its training code, run it on a laptop CPU, and see exactly where a model of this size is good and where it fails. - HellaSwag 33.6% (accnorm). That is above GPT-2 small (~30%) and below SmolLM2-135M (43.1%), which saw about 250x more training text. - The custom PyTorch code is included. The model does not use transformers; see How to use. This is QuickTalk run 8. "LMLM97M1" is its published name. 1. Learning and teaching how LLMs work. It is a complete, small, from-scratch GPT, with its training… Open weights apache-2.0 98M parameters pytorch [View model](https://savrn.com/models/lmlm-97m-1) Model · Text generation ### [lododo-Distill-v1.0-lora](https://savrn.com/models/lododo-distill-v1-0-lora) [Lododo.org](https://savrn.com/model-publishers/lododoai) Open weights apache-2.0 transformers [View model](https://savrn.com/models/lododo-distill-v1-0-lora) Model · Text generation ### [Longleaf-35B-A3B](https://savrn.com/models/longleaf-35b-a3b) [Red Hills Media](https://savrn.com/model-publishers/redhillsmediafl) Longleaf is our local model for coding and agent work: repository edits, debugging, structured tools, and clear answers. Built on Qwen3.6-35B-A3B. - 35B total / 3B active parameters. - MLX 4-bit weights. - 262,144-token configured context. EvalPlus 0.3.1, 164 tasks, pass@1. Thinking off, greedy sampling, 2,048-token output cap, 262,144-token configured context. Generation used our M1 Ultra 231 / 198 / 195 tokens, respectively. CLI sample: five Terminal-Bench 2 tasks on ARM64, thinking off. Per task: 300 seconds, 24 model calls, 32 tool calls, 2,048 output tokens per call. Our M1 Ultra Splash runtime, medium thinking, model already loaded: Read, edit, and test completed in about 6 seconds… Open weights apache-2.0 35.1B parameters 262,144 tokens mlx [View model](https://savrn.com/models/longleaf-35b-a3b) Model · Text generation ### [Longleaf-35B-A3B-Abliterated](https://savrn.com/models/longleaf-35b-a3b-abliterated) [Red Hills Media](https://savrn.com/model-publishers/redhillsmediafl) The abliterated version of Longleaf, our local model for coding, repository edits, debugging, and structured tools. - 35B total / 3B active parameters. - MLX 4-bit weights. - 262,144-token configured context. EvalPlus 0.3.1, 164 tasks, pass@1. Thinking off, greedy sampling, 2,048-token output cap, 262,144-token configured context. Generation used our M1 Ultra 231 / 198 / 195 tokens, respectively. CLI sample: five Terminal-Bench 2 tasks on ARM64, thinking off. Per task: 300 seconds, 24 model calls, 32 tool calls, 2,048 output tokens per call. Apache 2.0. This release contains modified model weights, based on Qwen3.6-35B-A3B, and the Abliteration changes refusal behavior, not output… Open weights apache-2.0 35.1B parameters 262,144 tokens mlx [View model](https://savrn.com/models/longleaf-35b-a3b-abliterated) Model · Text generation ### [LoopPolicy-27B-LoRA](https://savrn.com/models/looppolicy-27b-lora) [EnvLoop](https://savrn.com/model-publishers/envloop) 1d4bf0f2ff6012fd82039f2fa52739d0dd7c60c0) that answers typed decision questions for a personal agent with long-term memory, with calibrated probabilities. Code, pre-registration, results and technical report: - Unpacked from the frozen training output qwen-adapter.tar.gz, SHA-256 6b07a7d36eba59b9cfd9cf440bdc5783f4fc12d4d726cfa5beef2462860d8d81 (per-file hashes in release-manifest.json). - Frozen as the final candidate after two hill-climbing rounds; passed the one-shot pre-registered HIDDEN gate; then compared once with five other models on a public TEST set. LoopPolicy is the Hugging Face release name of the PersonaLoop research artifacts: a calibrated personal-agent policy built through… Access requested at publisher other peft [View model](https://savrn.com/models/looppolicy-27b-lora) Model · Text generation ### [LUHANADJolTctKlt](https://savrn.com/models/luhanadjoltctklt) [Priyansh Singhal](https://savrn.com/model-publishers/ps4research) This seedoss model was trained 2x faster with Unsloth and Huggingface's TRL library. Open weights apache-2.0 36.2B parameters 524,288 tokens transformers [View model](https://savrn.com/models/luhanadjoltctklt) Model · Text generation ### [luna-1.5-flash](https://savrn.com/models/luna-1-5-flash) [AobanZ](https://savrn.com/model-publishers/aobangaming) We introduce LUNA, a small, autoregressive transformer. This model aims to provide conversational-like chat without overloading the computer. This model is designed to run on small hardware, such as phones or office computers. Luna utilizes FlashAttention and AdamW for performance and capability. Lightning is designed to provide quick, coherent outputs, improved with a larger size and weight. Luna is intended to be used for research, analysis and fine-tuning, general conversation, stories and other. It is not intended to be used for professional advice, real writing or any kind of heavy work as generated outputs may be incorrect. Luna can be used directly for text generation… Open weights mit 43M parameters transformers [View model](https://savrn.com/models/luna-1-5-flash) Model · Text generation ### [Lurfa-1.3](https://savrn.com/models/lurfa-1-3) [Noeme](https://savrn.com/model-publishers/noeme) This is the model card of a transformers model that has been pushed on the Hub. Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. Use the code below to get started with the model. Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019). Open weights 494M parameters 32,768 tokens transformers [View model](https://savrn.com/models/lurfa-1-3) Model · Text generation ### [m-a-p__YuE-s2-1B-general](https://savrn.com/models/m-a-p-yue-s2-1b-general) [Allinsama](https://savrn.com/model-publishers/allinsama) Our model's name is YuE (乐). In Chinese, the word means "music" and "happiness." Some of you may find words that start with Yu hard to pronounce. If so, you can just call it "yeah." We wrote a song with our model's name. YuE is a groundbreaking series of open-source foundation models designed for music generation, specifically for transforming lyrics into full songs (lyrics2song). It can generate a complete song, lasting several minutes, that includes both a catchy vocal track and accompaniment track. YuE is capable of modeling diverse genres/languages/vocal techniques. Please visit the Demo Page for amazing vocal performance. Join Us on Discord! 2025.03.12 Paper Released: We now release… Open weights apache-2.0 2B parameters 8,192 tokens [View model](https://savrn.com/models/m-a-p-yue-s2-1b-general) Model · Text generation ### [Maillard-0.1-1.1B-Alpha](https://savrn.com/models/maillard-0-1-1-1b-alpha) [RenWuJun](https://savrn.com/model-publishers/renwujun) Open weights mit [View model](https://savrn.com/models/maillard-0-1-1-1b-alpha) Model · Text generation ### [MANAS](https://savrn.com/models/manas) [Mrittunjay Dubey](https://savrn.com/model-publishers/jayf14) A character-level causal Transformer trained on the literary corpus of Goswami Tulsidas MANAS is a small, experimental character-level causal Transformer language model trained on a Devanagari literary corpus focused on the works of Goswami Tulsidas — the 16th-century poet-saint and author of the Ramcharitmanas. Unlike modern large language models that operate on subword tokens (BPE, SentencePiece), MANAS processes text one Unicode character at a time. The model was built entirely from scratch in PyTorch, without any pretrained weights or transfer learning, as an educational experiment into whether a small Transformer can learn the statistical patterns of classical Awadhi poetry from raw… Open weights mit [View model](https://savrn.com/models/manas) Model · Text generation ### [Mangaba-Nano-1M](https://savrn.com/models/mangaba-nano-1m) [Mangaba AI](https://savrn.com/model-publishers/mangaba-ai) Um modelo de linguagem de 1,4 milhão de parâmetros, treinado do zero em português do Brasil pela Mangaba AI. Relatório técnico completo (dados, arquitetura, Muon, ablações, controles e destilação): https://huggingface.co/spaces/mangaba-ai/mangaba-nano-artigo Não há modelo base: os pesos começaram aleatórios e o tokenizer também foi treinado do zero sobre o mesmo corpus. O treino rodou nas GPUs NVIDIA L40S da própria Mangaba, em datacenter no Brasil. É um modelo de pesquisa e de borda: cabe em 5,6 MB, roda em qualquer CPU e serve como base para estudar escalas minúsculas, fazer ajuste fino em tarefas estreitas (classificação, autocompletar, extração simples) ou rodar em microcontroladores e… Open weights apache-2.0 1M parameters 512 tokens transformers [View model](https://savrn.com/models/mangaba-nano-1m) Model · Text generation ### [MANN-GPT](https://savrn.com/models/mann-gpt) [Wuff Mann](https://savrn.com/model-publishers/wuff-mann) 因果 MANN · 全局记忆 v2 · 动态思考网络（DTN） MANN-GPT v6 is a memory-augmented autoregressive language-model architecture built around causal MANN layers, a formally qualified Global Memory v2 path, and a Dynamic Thinking Network (DTN). This repository is the frozen architecture and code archive for the first formally qualified bilingual continuation line. MANN-GPT v6 是一种记忆增强型自回归语言模型架构，其核心由 因果 MANN 层（causal MANN layers）、已完成正式资格验证的 Global Memory v2 全局记忆路径，以及 动态思考网络（Dynamic Thinking Network, DTN） 构成。本仓库保存首条完成正式资格验证的中英双语继续训练线路所对应的冻结架构与代码归档。 The canonical Phase-1 checkpoint passed value qualification, Global-Memory causal-identity retention, exact Q2 preservation, fixed-D3 retention, strict autoregressive… Open weights mit [View model](https://savrn.com/models/mann-gpt) Model · Text generation ### [MarinSkyRL-Open-MOPD-SmolLM3-3B-step-32](https://savrn.com/models/marinskyrl-open-mopd-smollm3-3b-step-32) [Open Athena](https://savrn.com/model-publishers/open-athena) This is a MarinSkyRL-native Open-MOPD student after 32 optimizer steps. It starts from the authors' mixed-domain SFT checkpoint. Student responses were scored by the authors' math, code, and instruction-following RL teachers, routed by domain. The objective uses the student's selected top-16 token IDs and a clipped policy surrogate. This is an early checkpoint, not the authors' step-200 final model. The checkpoint is an unquantized, six-file Hugging Face export of the durable MarinSkyRL globalstep32 FSDP2 checkpoint. The policy export was used for the independent step-32 evaluation. The export's model.safetensors SHA-256 is bb7326640142069bc2e1fba5f54f15e0cccb1ff861f34f318b372eaab7abaf4b.… Open weights apache-2.0 3.3B parameters 65,536 tokens transformers [View model](https://savrn.com/models/marinskyrl-open-mopd-smollm3-3b-step-32) Model · Text generation ### [mario-html-4B-GGUF](https://savrn.com/models/mario-html-4b-gguf) [Wesjos Max](https://savrn.com/model-publishers/wesjos) A visual-UI language model fine-tuned from Qwen3.5-4B, quantized to GGUF for llama.cpp. It answers in a small semantic HTML component system — bento grids, metric cards, steppers, callouts — wrapped in one root, instead of plain Markdown. Reasoning-native, and no system prompt required. One root element; everything else is an optional child: ai-view-header is not in the source repo's theme.css — it renders with default header styling. Fine, but define your own if you want tighter control. Apache License 2.0. Open weights apache-2.0 transformers [View model](https://savrn.com/models/mario-html-4b-gguf) Model · Text generation ### [math-slm-qwen2.5-0.5b-v4](https://savrn.com/models/math-slm-qwen2-5-0-5b-v4) [Mandavi Singh](https://savrn.com/model-publishers/singhmandavi) A domain-specific small language model for step-by-step math problem solving, built by team03 (SLM Learners) for the Pramana SLM++ Bootcamp Round 2 submission. For an OpenAI-compatible endpoint, serve with servehf.py (stdlib + transformers only, no Ollama needed). Precision note: training ran in bf16 compute (QLoRA 4-bit NF4 base), but the merged checkpoint uploaded here is float16 (the merge step reloads the base in fp16). - Public Hugging Face datasets pulled via pulldata.py; licenses verified through the HF API on 2026-09-05 and recorded in datamanifest.md. - Held-out eval set built with buildheldouteval.py from raw ExamBench rows never used in training, with a final overlap check that… Open weights apache-2.0 494M parameters 32,768 tokens [View model](https://savrn.com/models/math-slm-qwen2-5-0-5b-v4) Model · Text generation ### [maxrl-no-eos-qwen3-1.7b-compression-bs32-n16-32k-146103-final](https://savrn.com/models/maxrl-no-eos-qwen3-1-7b-compression-bs32-n16-32k-146103-final) [Jiahao Zhang](https://savrn.com/model-publishers/hi-todayis-jh) Standard BF16 Hugging Face model, exported from training step 100. Weights, configuration, tokenizer, and the thinking chat template are at the repository root. Source checkpoint: hi-todayis-jh/maxrl-no-eos-qwen3-1.7b-compression-bs32-n16-32k-146103-step100 at commit 57eb43d677a67c0b80f242386b66f514b8838843. Load this repository directly with AutoModelForCausalLM.frompretrained or vLLM. Use enablethinking=True in the tokenizer chat template for the existing thinking evaluations. The export manifest records source provenance, file checksums, tensor validation, and a successful Transformers CPU load and forward pass. Open weights 2B parameters 40,960 tokens transformers [View model](https://savrn.com/models/maxrl-no-eos-qwen3-1-7b-compression-bs32-n16-32k-146103-final) Model · Text generation ### [Med-Qwen-3.5-4B-it](https://savrn.com/models/med-qwen-3-5-4b-it) [Adi Sann](https://savrn.com/model-publishers/adi274903) Open weights apache-2.0 4.2B parameters transformers [View model](https://savrn.com/models/med-qwen-3-5-4b-it) Model · Text generation ### [Meet8-0.6B](https://savrn.com/models/meet8-0-6b) [M7](https://savrn.com/model-publishers/ma7ee7) An experimental full-parameter post-training run by Ma7ee7, starting from Qwen/Qwen3-0.6B-Base. - Supervised fine-tuning on instruction, identity, human-written chat, generated FineWeb instruction examples, and generated creative writing. - Paired direct-answer and /think warmup using short reasoning examples. - Full-parameter GRPO on math, science, and logic tasks. - Approximately 3,500 total RL optimizer steps. Use the saved tokenizer chat template. The following system message substantially improves identity and reasoning-mode compliance: You are Meet8-0.6B, developed by Ma7ee7. If the user's message begins with /think, give a brief explanation inside..., then give your final response… Open weights 596M parameters 32,768 tokens transformers [View model](https://savrn.com/models/meet8-0-6b) Model · Text generation ### [Mellum2.1-12B-A2.5B-Thinking-GGUF](https://savrn.com/models/mellum2-1-12b-a2-5b-thinking-gguf) [Fares](https://savrn.com/model-publishers/thefaresmostafa) Open weights apache-2.0 gguf [View model](https://savrn.com/models/mellum2-1-12b-a2-5b-thinking-gguf) Model · Text generation ### [MemDuet-S2-7B](https://savrn.com/models/memduet-s2-7b) [Jiangcheng Song](https://savrn.com/model-publishers/jiangchengsong) Open weights apache-2.0 7.6B parameters transformers [View model](https://savrn.com/models/memduet-s2-7b) Model · Text generation ### [menasaat-qwen3-4b-oman-qlora-v2](https://savrn.com/models/menasaat-qwen3-4b-oman-qlora-v2) [Jaifar Alshizawi](https://savrn.com/model-publishers/jaifar) Second-generation LoRA adapter fine-tuning Qwen/Qwen3-4B (Apache 2.0) on a combined bilingual corpus: the Oman Wikipedia instruction set plus 1,095 tourism-grounded pairs from menasaat/menasaat-oman-tourism-places. مُحوِّل LoRA يُخصِّص Qwen3-4B على مجموعة موسّعة تجمع ويكيبيديا العُمانية وبيانات الأماكن السياحية. Tourism knowledge: opening hours, locations (wilaya/governorate), best visiting seasons, and visitor tips for 159 places across all 11 governorates — plus Arabic location questions (أين تقع...؟) answered from the dataset. Tourism answers are grounded in the compiled dataset; verify time-sensitive details (hours, seasons) before high-stakes use. General-knowledge capability matches… Open weights apache-2.0 peft [View model](https://savrn.com/models/menasaat-qwen3-4b-oman-qlora-v2) Model · Text generation ### [menasaat-qwen3-4b-oman-qlora-v2](https://savrn.com/models/menasaat-qwen3-4b-oman-qlora-v2-2) [Menasaat | Virtual Platforms LLC](https://savrn.com/model-publishers/menasaat) Second-generation LoRA adapter fine-tuning Qwen/Qwen3-4B (Apache 2.0) on a combined bilingual corpus: the Oman Wikipedia instruction set plus 1,095 tourism-grounded pairs from menasaat/menasaat-oman-tourism-places. مُحوِّل LoRA يُخصِّص Qwen3-4B على مجموعة موسّعة تجمع ويكيبيديا العُمانية وبيانات الأماكن السياحية. Tourism knowledge: opening hours, locations (wilaya/governorate), best visiting seasons, and visitor tips for 159 places across all 11 governorates — plus Arabic location questions (أين تقع...؟) answered from the dataset. Tourism answers are grounded in the compiled dataset; verify time-sensitive details (hours, seasons) before high-stakes use. General-knowledge capability matches… Open weights apache-2.0 peft [View model](https://savrn.com/models/menasaat-qwen3-4b-oman-qlora-v2-2) Model · Text generation ### [MiMo-V2.6-Flash-RL](https://savrn.com/models/mimo-v2-6-flash-rl) [Xiaomi MiMo](https://savrn.com/model-publishers/xiaomimimo) Scaling Reinforcement Learning Toward Self-Improvement MiMo-V2.6-Flash-RL is the efficiency-balanced checkpoint of the MiMo-V2.6 series. The series is built to scale reinforcement learning toward self-improvement — scaling RL compute, environment diversity, and grader compute together, so the model keeps expanding its capability frontier through exploration and feedback. Key features include: - Native Omnimodal + Long Horizon: Text, image, video, and audio in one model; 1M tokens for long repositories, tool traces, and multi-session agent runs. - Multi-Prefix Multi-Teacher On-Policy Distillation (MOPD2): After mixed RL, MOPD2 combines autonomous student rollouts with prefix-conditioned… Open weights mit 159.4B parameters 1,048,576 tokens transformers [View model](https://savrn.com/models/mimo-v2-6-flash-rl) Model · Text generation ### [MiMo-V2.6-Flash-RL](https://savrn.com/models/mimo-v2-6-flash-rl-2) [Zachary Howard](https://savrn.com/model-publishers/servantofares) Scaling Reinforcement Learning Toward Self-Improvement MiMo-V2.6-Flash-RL is the efficiency-balanced checkpoint of the MiMo-V2.6 series. The series is built to scale reinforcement learning toward self-improvement — scaling RL compute, environment diversity, and grader compute together, so the model keeps expanding its capability frontier through exploration and feedback. Key features include: - Native Omnimodal + Long Horizon: Text, image, video, and audio in one model; 1M tokens for long repositories, tool traces, and multi-session agent runs. - Multi-Prefix Multi-Teacher On-Policy Distillation (MOPD2): After mixed RL, MOPD2 combines autonomous student rollouts with prefix-conditioned… Open weights mit 159.4B parameters 1,048,576 tokens transformers [View model](https://savrn.com/models/mimo-v2-6-flash-rl-2) Model · Text generation ### [MiMo-V2.6-Pro-EXL3](https://savrn.com/models/mimo-v2-6-pro-exl3) [Jarrel Seah](https://savrn.com/model-publishers/jarrelscy) Open weights custom [View model](https://savrn.com/models/mimo-v2-6-pro-exl3) Model · Text generation ### [MiMo-V2.6-Pro-RL](https://savrn.com/models/mimo-v2-6-pro-rl) [Xiaomi MiMo](https://savrn.com/model-publishers/xiaomimimo) Scaling Reinforcement Learning Toward Self-Improvement MiMo-V2.6-Pro-RL is the flagship checkpoint of the MiMo-V2.6 series. The series is built to scale reinforcement learning toward self-improvement — scaling RL compute, environment diversity, and grader compute together, so the model keeps expanding its capability frontier through exploration and feedback. Key features include: - Native Omnimodal + Long Horizon: Text, image, video, and audio in one model; 1M tokens for long repositories, tool traces, and multi-session agent runs. - Multi-Prefix Multi-Teacher On-Policy Distillation (MOPD2): After mixed RL, MOPD2 combines autonomous student rollouts with prefix-conditioned single-turn… Open weights mit 524.1B parameters 1,048,576 tokens transformers [View model](https://savrn.com/models/mimo-v2-6-pro-rl) Model · Text generation ### [MiMo-V2.6-Pro-RL](https://savrn.com/models/mimo-v2-6-pro-rl-2) [Zachary Howard](https://savrn.com/model-publishers/servantofares) Scaling Reinforcement Learning Toward Self-Improvement MiMo-V2.6-Pro-RL is the flagship checkpoint of the MiMo-V2.6 series. The series is built to scale reinforcement learning toward self-improvement — scaling RL compute, environment diversity, and grader compute together, so the model keeps expanding its capability frontier through exploration and feedback. Key features include: - Native Omnimodal + Long Horizon: Text, image, video, and audio in one model; 1M tokens for long repositories, tool traces, and multi-session agent runs. - Multi-Prefix Multi-Teacher On-Policy Distillation (MOPD2): After mixed RL, MOPD2 combines autonomous student rollouts with prefix-conditioned single-turn… Open weights mit 524.1B parameters 1,048,576 tokens transformers [View model](https://savrn.com/models/mimo-v2-6-pro-rl-2) Model · Text generation ### [Mini-K3-1H-attn-1kda-3mla-nope-v2](https://savrn.com/models/mini-k3-1h-attn-1kda-3mla-nope-v2) [Nkkbr](https://savrn.com/model-publishers/nkkbr) This repository contains a text-only Mini-K3-1H v2 pretraining checkpoint from a controlled 20-architecture comparison. The family retains Kimi-K3's KDA and Gated MLA operators, block Attention Residuals, Stable LatentMoE, SiTU activations, output gates, and Quantile Balancing at approximately one billion logical parameters. The exact architecture for this repository is listed below; some ablations deliberately replace the baseline KDA/MLA ratio, decay granularity, convolution length, or positional encoding. - Hidden width / attention heads / KDA head width: 1024 / 12 / 128 - Vocabulary / BOS / generation EOS / PAD: 163840 / 163584 / 163586 / 163839 control state retained in FP32 where… Open weights 993M parameters 131,072 tokens pytorch [View model](https://savrn.com/models/mini-k3-1h-attn-1kda-3mla-nope-v2) Model · Text generation ### [Mini-K3-1H-attn-2kda-2mla-nope-v2](https://savrn.com/models/mini-k3-1h-attn-2kda-2mla-nope-v2) [Nkkbr](https://savrn.com/model-publishers/nkkbr) This repository contains a text-only Mini-K3-1H v2 pretraining checkpoint from a controlled 20-architecture comparison. The family retains Kimi-K3's KDA and Gated MLA operators, block Attention Residuals, Stable LatentMoE, SiTU activations, output gates, and Quantile Balancing at approximately one billion logical parameters. The exact architecture for this repository is listed below; some ablations deliberately replace the baseline KDA/MLA ratio, decay granularity, convolution length, or positional encoding. - Hidden width / attention heads / KDA head width: 1024 / 12 / 128 - Vocabulary / BOS / generation EOS / PAD: 163840 / 163584 / 163586 / 163839 control state retained in FP32 where… Open weights 1B parameters 131,072 tokens pytorch [View model](https://savrn.com/models/mini-k3-1h-attn-2kda-2mla-nope-v2) Model · Text generation ### [Mini-K3-1H-attnres-block1-v1_D](https://savrn.com/models/mini-k3-1h-attnres-block1-v1-d) [Nkkbr](https://savrn.com/model-publishers/nkkbr) This repository contains a text-only Mini-K3-1H checkpoint from the controlled Attention Residuals follow-up study. The comparison includes standard PreNorm, three block granularities, and full sublayer-level AttnRes. The original Block-4 baseline is the separately published nkkbr/Mini-K3-1H-v2; this model's only architectural change is the depth-wise residual mechanism. - Hidden width / attention heads / KDA head width: 1024 / 12 / 128 - Residual mode / decoder layers per block: block / 1 - Vocabulary / BOS / generation EOS / PAD: 163840 / 163584 / 163586 / 163839 control state retained in FP32 where defined by the implementation Every numbered checkpoint is an immutable Git tag. main… Open weights 1B parameters 131,072 tokens pytorch [View model](https://savrn.com/models/mini-k3-1h-attnres-block1-v1-d) Model · Text generation ### [Mini-K3-1H-kda-kernel-1-v2](https://savrn.com/models/mini-k3-1h-kda-kernel-1-v2) [Nkkbr](https://savrn.com/model-publishers/nkkbr) This repository contains a text-only Mini-K3-1H v2 pretraining checkpoint from a controlled 20-architecture comparison. The family retains Kimi-K3's KDA and Gated MLA operators, block Attention Residuals, Stable LatentMoE, SiTU activations, output gates, and Quantile Balancing at approximately one billion logical parameters. The exact architecture for this repository is listed below; some ablations deliberately replace the baseline KDA/MLA ratio, decay granularity, convolution length, or positional encoding. - Hidden width / attention heads / KDA head width: 1024 / 12 / 128 - Vocabulary / BOS / generation EOS / PAD: 163840 / 163584 / 163586 / 163839 control state retained in FP32 where… Open weights 1B parameters 131,072 tokens pytorch [View model](https://savrn.com/models/mini-k3-1h-kda-kernel-1-v2) Model · Text generation ### [MiniCPM5-2B-Math](https://savrn.com/models/minicpm5-2b-math) [Caldalis](https://savrn.com/model-publishers/caldalis) English | MiniCPM5-2B-Math is a math and proof model built on MiniCPM5: a dense 2.5B model based on MiniCPM5-2B and post-trained for long-form mathematical reasoning and proof writing. It runs on a single consumer GPU or a laptop and keeps the native 128K context. - Strong for its size. As a plain single call with up to 128K tokens of thinking, 92.3 on AIME 2025, 89.8 on AIME 2026 and 81.8 on HMMT February 2026 (avg@16), and 100 / 93.3 / 90.9 with a 16-sample vote. The official general-purpose MiniCPM5-2B scores 87.1 / 89.8 / 68.4 under the same protocol. - Writes checkable proofs. On IMO-ProofBench Basic, an average single call with up to 128K tokens writes a complete proof for 21 of the… Open weights apache-2.0 2.5B parameters 131,072 tokens transformers [View model](https://savrn.com/models/minicpm5-2b-math) Model · Text generation ### [MiniCPM5-2B-Math-GGUF](https://savrn.com/models/minicpm5-2b-math-gguf) [Caldalis](https://savrn.com/model-publishers/caldalis) GGUF builds of MiniCPM5-2B-Math, a 2.5B math and proof specialist, for llama.cpp, Ollama and LM Studio. Pair it with the MiniCPM-Math Harness to run a small proof swarm on a laptop. Converted with llama.cpp b10964 (converthftogguf.py, tokenizer pre-type minicpm5) and quantized with llama-quantize. The files load on llama.cpp b9354 or newer, which added the MiniCPM5 tokenizer; use b9833 or newer, which added the MiniCPM5 chat parser that separates the reasoning from the answer. The recommended sampling settings (temperature 0.9, top-p 0.95, min-p 0, top-k off) are embedded in the GGUF metadata, so llama.cpp uses them by default. All results on the model card were measured with the BF16… Open weights apache-2.0 gguf [View model](https://savrn.com/models/minicpm5-2b-math-gguf) Model · Text generation ### [minimind-math-v3](https://savrn.com/models/minimind-math-v3) [Jiwubu](https://savrn.com/model-publishers/jiwubu) minimind-math-v3 是一个基于 MiniMind 项目从零训练的小型中文数学语言模型，权重已转换为 Qwen3 兼容格式，可直接使用 HuggingFace transformers 加载推理。 - 架构：Dense Transformer（Decoder-only），未使用 MoE - 数据：以数学/推理语料为主的预训练数据（pretraint2tmini.jsonl），并经过数学 SFT 训练 - Tokenizer：基于 MiniMind 自训 tokenizer 修改的 patched tokenizer，详见下方说明 本模型的预训练与 SFT 均基于 jiwubu/minimind 代码仓库完成。相对上游 jingyaogong/minimind 的主要修改是新增 math/ 目录，用于生成数学 SFT 用的加减乘除算术数据（genmathdataaddsub.py、genmathdatamuldiv.py 等），并提供配套评测脚本（evalmath.py）。 最简单的方式是用仓库自带的交互式验证脚本（chat template + 贪心解码 + 流式输出）： 或直接用 transformers： - 预训练 2 个 epoch，batch size 32，最大序列长度 340 - 优化器 AdamW，初始学习率 5e-4（带 warmup + 余弦衰减） - 混合精度：bfloat16 本模型使用基于 MiniMind 原版 tokenizer 修改的 patched tokenizer（Sequence[Digits, ByteLevel]）：… Open weights apache-2.0 64M parameters 32,768 tokens transformers [View model](https://savrn.com/models/minimind-math-v3) Model · Text generation ### [Ministral-3-8B-Instruct-2512-matura-grpo-lora-closed-em](https://savrn.com/models/ministral-3-8b-instruct-2512-matura-grpo-lora-closed-em) [WMTH-100d2exam](https://savrn.com/model-publishers/wmth-100d2exam) Ministral-3-8B-Instruct-2512 post-trained for the Polish history matura (extended level) during the Warsaw Model Trainers alpha=64) on top of mistralai/Ministral-3-8B-Instruct-2512-BF16 (the bf16 twin of the FP8 -2512 release). closedem = exact match on closed items. Graded scores (deepseek-flash-high@think via benchmark/bench.py) are reported separately. Open weights apache-2.0 262,144 tokens transformers [View model](https://savrn.com/models/ministral-3-8b-instruct-2512-matura-grpo-lora-closed-em) Model · Text generation ### [Ministral-3-8B-Instruct-2512-matura-sft-grpo-lora-closed-em](https://savrn.com/models/ministral-3-8b-instruct-2512-matura-sft-grpo-lora-closed-em) [WMTH-100d2exam](https://savrn.com/model-publishers/wmth-100d2exam) Ministral-3-8B-Instruct-2512 post-trained for the Polish history matura (extended level) during the Warsaw Model Trainers alpha=64) on top of mistralai/Ministral-3-8B-Instruct-2512-BF16 (the bf16 twin of the FP8 -2512 release). closedem = exact match on closed items. Graded scores (deepseek-flash-high@think via benchmark/bench.py) are reported separately. Open weights apache-2.0 262,144 tokens transformers [View model](https://savrn.com/models/ministral-3-8b-instruct-2512-matura-sft-grpo-lora-closed-em) Model · Text generation ### [Ministral-3-8B-Instruct-2512-matura-sft-lora-distill-epod](https://savrn.com/models/ministral-3-8b-instruct-2512-matura-sft-lora-distill-epod) [WMTH-100d2exam](https://savrn.com/model-publishers/wmth-100d2exam) Ministral-3-8B-Instruct-2512 post-trained for the Polish history matura (extended level) during the Warsaw Model Trainers alpha=64) on top of mistralai/Ministral-3-8B-Instruct-2512-BF16 (the bf16 twin of the FP8 -2512 release). closedem = exact match on closed items. Graded scores (deepseek-flash-high@think via benchmark/bench.py) are reported separately. Open weights apache-2.0 peft [View model](https://savrn.com/models/ministral-3-8b-instruct-2512-matura-sft-lora-distill-epod) Model · Text generation ### [ministral-8b-tlink-sentence-only-autoregressive](https://savrn.com/models/ministral-8b-tlink-sentence-only-autoregressive) [Anirban Saha Anik](https://savrn.com/model-publishers/anirbansaha) Full-parameter fine-tuning for TLINK temporal relation classification. mistralai/Ministral-8B-Instruct-2410 AnirbanSaha/tlink-classification-sentence-only The evaluation/ directory contains predictions, the classification report, confusion matrix, and a machine-readable evaluation summary. Open weights 8B parameters 32,768 tokens transformers [View model](https://savrn.com/models/ministral-8b-tlink-sentence-only-autoregressive) Model · Text generation ### [mistral-7b-qlora-alpaca-sample-0.5k](https://savrn.com/models/mistral-7b-qlora-alpaca-sample-0-5k) [Seongmin Kim](https://savrn.com/model-publishers/mrseongminkim) This is the model card of a transformers model that has been pushed on the Hub. Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. Use the code below to get started with the model. Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019). Open weights 7.2B parameters 32,768 tokens transformers [View model](https://savrn.com/models/mistral-7b-qlora-alpaca-sample-0-5k) Model · Text generation ### [Mistral-Small-22B-ArliAI-RPMax-v1.1-GGUF](https://savrn.com/models/mistral-small-22b-arliai-rpmax-v1-1-gguf) [Dan](https://savrn.com/model-publishers/dan517) Using llama.cpp release b3825 for quantization. Original model: https://huggingface.co/ArliAI/Mistral-Small-22B-ArliAI-RPMax-v1.1 All quants made using imatrix option with dataset from here Run them in LM Studio Some of these quants (Q3KXL, Q4KL etc) are the standard quantization method with the embeddings and output weights quantized to Q80 instead of what they would normally default to. Some say that this improves the quality, others don't notice any difference. If you use these models PLEASE COMMENT with your findings. I would like feedback that these are actually used and useful so I don't keep uploading quants no one is using. Thanks! First, make sure you have hugginface-cli installed… Open weights other [View model](https://savrn.com/models/mistral-small-22b-arliai-rpmax-v1-1-gguf) Model · Text generation ### [mixture-of-tiny-sliding-experts](https://savrn.com/models/mixture-of-tiny-sliding-experts) [Hallford](https://savrn.com/model-publishers/ehraim) One frozen public checkpoint is loaded at a time on a 24 GB GPU. A hash router picks it. Optional chains pass text from one expert to the next. A bag of those chains votes on the final string. A separate 128-dimensional cache, shared only by the routers, can slide along the chain. This repository is an assembly of published methods. It does not introduce a new routing, memory, or decoding algorithm. The bibliography at the bottom is the full set of ideas used in the code. Upstream weight files keep their own licenses and are not redistributed here. A request is hashed into a bag of word ids. A small classifier scores 138 expert ids. Confidence under 0.45 selects the int4 14B coder. An image… Open weights other mote [View model](https://savrn.com/models/mixture-of-tiny-sliding-experts) Model · Text generation ### [Mochi-1.5](https://savrn.com/models/mochi-1-5) [Eli Grenn](https://savrn.com/model-publishers/stupidlime) A small, unprofessional fine-tune of Qwen 2.5, made to have a slightly different personality. Based on huihui-ai/Qwen2.5-0.5B-Instruct-abliterated-v3. Mochi prioritizes having multiple different variants of the base model for different purposes, always using 0.5B parameters. It is only made for fun, and has no actual use if you're looking for something powerful or coherent. - No system prompt required. The personality is now baked in by default. You can still pass a system prompt to adjust behavior, but the Mochi vibe works without one. - Cleaner dataset. 868 examples, all without system prompts, so the model doesn't depend on one to behave correctly. - Factual accuracy is degraded compared… Open weights apache-2.0 [View model](https://savrn.com/models/mochi-1-5) Model · Text generation ### [mojolearn-162m](https://savrn.com/models/mojolearn-162m) [Andrew Hendel](https://savrn.com/model-publishers/ajhendel) A 162M-parameter decoder trained twice from the same initialization on the same 2.62 billion FineWeb-Edu tokens, once along each of two different routes through NVIDIA, AMD and Apple GPUs. The two runs are bitwise identical at every one of the 5,000 optimizer steps: training state, summed gradients, all 64 per-shard losses and the learning rate. Their final checkpoint files have the same SHA-256. This repository distributes that one final model with the evidence from both routes. The model is GPT-3 Small-sized and trained with GPT-3 Small's hyperparameters, but its blocks are modern Llama-style blocks; see the comparison below. It is a research artifact for reproducible training, not a… Open weights apache-2.0 162M parameters 2,048 tokens mojolearn [View model](https://savrn.com/models/mojolearn-162m) Model · Text generation ### [moondream3.1-9B-A2B-GGUF](https://savrn.com/models/moondream3-1-9b-a2b-gguf) [Amaimediacom](https://savrn.com/model-publishers/amaimedia) Local hardware: Mechrevo Kuangshi GM7AG0M — RTX 3060 Laptop 6GB GDDR6, 64GB DDR5, i7-12700H (14C/20T, 4.7GHz), Windows 11, Samsung 990 Pro. Good for imatrix and 0.6–35B-class work in RAM. 9B+ and searches need rented H200/Blackwell, typically $100 per quant. Released as part of the NOESIS Professional Multilingual Dubbing Automation Platform (framework: Deterministic Hybrid Control Framework for Frozen Neural Operators — DHCF-FNO). GGUF-конвертация и кванты текстового бэкбона Moondream 3.1 — vision-language модели с MoE-архитектурой (9B всего / 2B активных параметров). Конвертация и квантование выполнены AMAImedia; vision-часть (mmproj) в репозиторий не входит. Все файлы… Open weights other llama.cpp [View model](https://savrn.com/models/moondream3-1-9b-a2b-gguf) Model · Text generation ### [Morpho-72B-MoE](https://savrn.com/models/morpho-72b-moe) [Blue Morpho Limited](https://savrn.com/model-publishers/bluemorpholimited) 180B total / ~78B active per request — giant knowledge, agile inference. - 64 domain experts, zero overlap — every training example maps to exactly one expert. Auditable by construction. - Fully auditable data pipeline — raw → tagged → tokenized corpora, code included, in Morpho-72B-MoE-Data. - Resume-first engineering — every expert checkpoint (weights + loss + step) is versioned in Morpho-72B-MoE-Checkpoints. Any box can pick up exactly where the last one died. - 128K context via RoPE YaRN for long documents, codebases, and books. Eight sectors — Finance, Law, Medicine, Tech, Science, Business, Arts, Humanities — each with 8 specialists. Full roster with per-expert data counts is logged… Open weights apache-2.0 [View model](https://savrn.com/models/morpho-72b-moe) Model · Text generation ### [Morpho-72B-MoE-DPO](https://savrn.com/models/morpho-72b-moe-dpo) [Blue Morpho Limited](https://savrn.com/model-publishers/bluemorpholimited) Stage 5 of the Morpho-180B pipeline (display name; SFT backbone: - Per-expert DPO, same 64 experts, same one-example-one-expert mapping as SFT. - Real preference data only (HH-RLHF, HelpSteer2, UltraFeedback, Nectar), routed per expert by the v5 taxonomy. - DPO adapters initialize from the converged SFT adapters — never from scratch. Stage 5 IN PROGRESS — 17/31 experts DONE (resumed 3x, AUTOSKIP active, final leg running on 97GB GPU box). 24 eligible experts remain in the queue; 33 thin experts (<200 pairs) keep SFT-only per policy. Each row is verified from the expert's bestloss.txt + DONE.txt on this repo. Progress tracked on the model card. Open weights apache-2.0 [View model](https://savrn.com/models/morpho-72b-moe-dpo) Model · Text generation ### [motif-3-bh-galaxy](https://savrn.com/models/motif-3-bh-galaxy) [Hyunggi Chang](https://savrn.com/model-publishers/changh95) This package runs the Motif-3 LLM of Motif Technologies on one Tenstorrent Blackhole Galaxy (32 Blackhole chips). - 53 layers of Grouped Differential Latent Attention (GDLA). - A 4-stream mHC residual. - 384 routed experts and 1 shared expert, all PolyNorm MLPs, with top-8 routing. - 1 MTP (multi-token-prediction) layer. - default: for all traffic. - mtp (opt-in): greedy requests decode up to 1.9× faster with the model's own MTP layer. - Built on tt-metal / ttnn as a plain vLLM model behind the vllm-tt-plugin. - Mesh (4, 8): attention is 8-way tensor-parallel in 4 groups of 8 user lanes; the MoE is 32-way expert-parallel (12 experts per chip). - Decode runs as captured Metal traces. The MTP… Open weights mit [View model](https://savrn.com/models/motif-3-bh-galaxy) Model · Text generation ### [my-qwen-lora-cisco](https://savrn.com/models/my-qwen-lora-cisco) [SN](https://savrn.com/model-publishers/banhcarrot) A merged (LoRA-finetuned) variant of Qwen/Qwen2.5-1.5B-Instruct, fine-tuned for Cisco-related assistant tasks. This repository contains full merged weights — not a PEFT adapter. Load it directly with transformers; no peft and no adapter merging step is required. The model is tagged endpointscompatible and can be deployed directly to for a dedicated, OpenAI-compatible /v1/chat/completions API. Direct use: [e.g. answering Cisco product, configuration, and troubleshooting questions.] Out of scope: This model is not production-grade for safety- or compliance-critical networking decisions. Verify all configuration and command output before applying it to real hardware. Do not use it as the sole… Open weights apache-2.0 1.5B parameters 32,768 tokens transformers [View model](https://savrn.com/models/my-qwen-lora-cisco) Model · Text generation ### [NadevA23_Kronumos-Kairos-v2-GGUF](https://savrn.com/models/nadeva23-kronumos-kairos-v2-gguf) [Bartowski](https://savrn.com/model-publishers/bartowski) Using llama.cpp release b11259 for quantization. Don't know which to choose? Grab Q4KM (4.78GB) - usually a good mix of size and performance. Download instructions available here First, make sure you have the Hugging Face CLI installed: These quants run with llama.cpp - installable in one line via llama.app: llama-server includes a built-in chat web UI, served at http://localhost:8080 by default. These quants were made with llama.cpp release b11259 - if this model's architecture is newly supported, you'll need that release or newer to run them. They also work in: quants made using imatrix option, with a calibration corpus rendered through this model's own chat template. The corpus pairs… Open weights apache-2.0 transformers [View model](https://savrn.com/models/nadeva23-kronumos-kairos-v2-gguf) Model · Text generation ### [nanites-smoky-1b-chat](https://savrn.com/models/nanites-smoky-1b-chat) [Nanites](https://savrn.com/model-publishers/nanite-labs) A Llama-3.2-1B-Instruct model fine-tuned to play the role of an old resident of the Great Smoky Mountains of the 1930s in conversation. You talk to it; the old-timer answers in period voice with regional vocabulary. This is the chat-tuned sibling of the CosyVoice2 gender-pooled speech voices (Earl / male at Nanite-Labs/nanites-smoky-speech-earl, Ethel / female at Nanite-Labs/nanites-smoky-speech-ethel). The chat model provides the language behind the TTS; pair them for a text-and-speech experience. Given a modern-English question about life in the Smokies (work, family, food, music, religion, hardships, the mountains themselves), the model answers in 1-3 sentences in the voice of an old… Open weights apache-2.0 1.2B parameters 131,072 tokens peft [View model](https://savrn.com/models/nanites-smoky-1b-chat) Model · Text generation ### [nanites-smoky-1b-chat-gguf](https://savrn.com/models/nanites-smoky-1b-chat-gguf) [Nanites](https://savrn.com/model-publishers/nanite-labs) Q4KM quant of the merged nanites-smoky-1b-chat model — a Llama-3.2-1B-Instruct fine-tune that plays an old resident of the Great Smoky Mountains of the 1930s. For Ollama / LM Studio / llama.cpp users who don't want the base-model + adapter merge step. Adapter (train output) lives at Nanite-Labs/nanites-smoky-1b-chat; this repo holds the merged + quantized GGUF for direct use. Alpaca-style (### Instruction: / ### Input: / ### Response:). Example prompt Open weights apache-2.0 [View model](https://savrn.com/models/nanites-smoky-1b-chat-gguf) Model · Text generation ### [nanites-whaler-1b-chat](https://savrn.com/models/nanites-whaler-1b-chat) [Nanites](https://savrn.com/model-publishers/nanite-labs) A Llama-3.2-1B-Instruct model fine-tuned to play the role of a 19th-century American whaling first mate in conversation. You talk to it; the mate answers in period voice. This is the chat-tuned sibling of Nanite-Labs/nanites-whaler-1b, which is a text completer that continues 19th-century whaling logbook entries. The chat version is a different animal — don't mix them up. Talk to it like a sailor would talk to the mate on deck. It answers in the voice of a 19th-c. ship's mate, brief and direct, using "try-works", "by D.R.", "the Captain", "no speak of it", etc. Multi-turn is supported — the mate sees your prior Q&A in the context window and can refer to earlier exchanges. period voice) + 8… Open weights apache-2.0 1.2B parameters 131,072 tokens peft [View model](https://savrn.com/models/nanites-whaler-1b-chat) Model · Text generation ### [nanites-whaler-1b-chat-gguf](https://savrn.com/models/nanites-whaler-1b-chat-gguf) [Nanites](https://savrn.com/model-publishers/nanite-labs) Q4KM quant of the merged nanites-whaler-1b-chat model — a Llama-3.2-1B-Instruct fine-tune that plays a 19th-century American whaling first mate. For Ollama / LM Studio / llama.cpp users who don't want the base-model + adapter merge step. Adapter (train output) lives at Nanite-Labs/nanites-whaler-1b-chat; this repo holds the merged + quantized GGUF for direct use. Alpaca-style (### Instruction: / ### Input: / ### Response:). Example prompt Open weights apache-2.0 [View model](https://savrn.com/models/nanites-whaler-1b-chat-gguf) Model · Text generation ### [nanoBeard-sloop-14M](https://savrn.com/models/nanobeard-sloop-14m) [Lo Jahn](https://savrn.com/model-publishers/ihatetomatoes) A tiny pirate-themed GPT trained from scratch on a piratized version of TinyStories, then SFT-tuned. Built as a learning project — closer to nanoGPT than to a production LM. - model.safetensors — model weights. - config.json — architecture config (load into training.config.Config). - piratebpe.json — tokenizer (load with tokenizers.Tokenizer.fromfile). - trainingmetadata.json — full training config + metrics snapshot. - banner.png — the banner above. This model is not a transformers model — it uses the custom GPT class from this repo. - Trained on a small synthetic corpus (TinyStories, piratized). Vocabulary, grammar, and world knowledge are extremely narrow. - Short context window (256… Open weights 14M parameters pytorch [View model](https://savrn.com/models/nanobeard-sloop-14m) Model · Text generation ### [nanogpt-shakespeare-char](https://savrn.com/models/nanogpt-shakespeare-char) [Ricardo Jose Dos Santos Cruz](https://savrn.com/model-publishers/ricardojscruz1963) This is the model card of a transformers model that has been pushed on the Hub. Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. Use the code below to get started with the model. Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019). Open weights 11M parameters transformers [View model](https://savrn.com/models/nanogpt-shakespeare-char) Model · Text generation ### [nanolang-bitnet-b158-700m](https://savrn.com/models/nanolang-bitnet-b158-700m) [Bagas Sukma Alamsyah](https://savrn.com/model-publishers/dracko14) Open weights mit nanow [View model](https://savrn.com/models/nanolang-bitnet-b158-700m) Model · Text generation ### [Naphula_Goetia-26B-A4B-v1.7-APEX-GGUF](https://savrn.com/models/naphula-goetia-26b-a4b-v1-7-apex-gguf) [Nick Pario](https://savrn.com/model-publishers/npario) This repo contains some APEX quantizations of Naphula/Goetia-26B-A4B-v1.7, created using bartowski's imatrix found here. As explained by its creators, APEX is "a novel MoE-aware mixed-precision quantization technique for llama.cpp". I suggest reading their information on the how and why of the method. Quantized using llama.cpp #1692f9e50 For roleplaying, I personally strongly recommend nohurry's SillyTavern presets for Gemma 4 models. My only contribution is compute. This is neither my merge, nor my quantization methodology. Have fun (within the constraints of the license). Google - the base model. Naphula - the Mergelord. Everyone whose finetunes were included in the merge! mudler - for… Open weights gemma llama.cpp [View model](https://savrn.com/models/naphula-goetia-26b-a4b-v1-7-apex-gguf) Model · Text generation ### [ncm-checkpoints](https://savrn.com/models/ncm-checkpoints) [HazyResearch](https://savrn.com/model-publishers/hazyresearch) Released tokenizer and generator pairs for Next-Concept Modeling. Each folder holds a config.yaml with the architecture and sampling settings and the.pt checkpoints it names. Open weights mit [View model](https://savrn.com/models/ncm-checkpoints) ## Questions ### Which Text generation models are most downloaded? By monthly downloads reported by the Hugging Face Hub: . ## Other Tasks - [Image and Text to Text](https://savrn.com/models/tasks/image-and-text-to-text) 588 - [Robotics](https://savrn.com/models/tasks/robotics) 403 - [Feature Extraction](https://savrn.com/models/tasks/feature-extraction) 400 - [Text Classification](https://savrn.com/models/tasks/text-classification) 335 - [Text to Image](https://savrn.com/models/tasks/text-to-image) 236 - [Speech Recognition](https://savrn.com/models/tasks/speech-recognition) 190 - [Text to Speech](https://savrn.com/models/tasks/text-to-speech) 148 - [Image Classification](https://savrn.com/models/tasks/image-classification) 140 - [Audio Classification](https://savrn.com/models/tasks/audio-classification) 130 - [Sentence Similarity](https://savrn.com/models/tasks/sentence-similarity) 103 - [Reinforcement Learning](https://savrn.com/models/tasks/reinforcement-learning) 102 - [Token Classification](https://savrn.com/models/tasks/token-classification) 101 [See all](https://savrn.com/models/tasks)