Search public pages, research tools, and SAVRN solutions.
SAVRN Model Hub · Models by License
3,344 open-weight models released under Apache License 2.0 in the SAVRN Model Hub, with Team Mradermacher, Qwen and Google publishing the most.
The Apache License 2.0 is a permissive open-source license. It permits commercial use, modification and redistribution. It requires keeping the license and copyright notices and any NOTICE file, stating significant changes, and it includes an express patent grant from contributors. Read the license text.
Apache 2.0 asks little of the operator. Commercial use, modification and redistribution are all permitted. What it requires is housekeeping: keep the license and copyright notices, carry any NOTICE file along with the weights, and state the significant changes if you pass a modified version on. It also includes an express patent grant from contributors, the clause a procurement reviewer looks for before a model serves paying customers. So an organization can take the files from the publisher, fine-tune on its own data, run the result in its own facility and bill for the output.
On our hub 1,018 models carry this license. Qwen leads with 81, Google 50, Convergent Intelligence 39, PyTorch Image Models 32, OpenMed 31, Helsinki-NLP Research Group 27, and Unsloth AI and PaddlePaddle 22 each. Text generation accounts for 164 of the models, image and text to text for 89, and robotics for 43, so it covers more than chat.
Downloads show where it runs. all-MiniLM-L6-v2 from Sentence Transformers, a 23M parameter sentence similarity model, pulls 255,050,544 downloads a month and needs 0.1 GB at 16-bit, small enough to ride on a GPU already serving. ms-marco-MiniLM-L6-v2 follows at 88,642,387 for text ranking. The one text generation model in the top eight is Qwen3-0.6B at 22,498,727 downloads a month: 752M parameters, a 40,960 token context, 1.8 GB at 16-bit, and the cheapest host on the Index for it is one MI300X at $1.85 an hour.
| Model | Publisher | Parameters | License | Monthly downloads | Cheapest GPUs at 16-bit |
|---|---|---|---|---|---|
| all-MiniLM-L6-v2 | Sentence Transformers | 23M | apache-2.0 | 198.6M | 1x MI300X, $1.85/hr |
| ms-marco-MiniLM-L6-v2 | Sentence Transformers - Cross-Encoders | 23M | apache-2.0 | 73.1M | 1x MI300X, $1.85/hr |
| paraphrase-multilingual-MiniLM-L12-v2 | Sentence Transformers | 118M | apache-2.0 | 41.9M | 1x MI300X, $1.85/hr |
| electra-base-discriminator | — | apache-2.0 | 38.9M | — | |
| bert-base-uncased | BERT community | 110M | apache-2.0 | 28.9M | 1x MI300X, $1.85/hr |
| Qwen3-0.6B | Qwen | 752M | apache-2.0 | 26.7M | 1x MI300X, $1.85/hr |
| t5-small | T5 community | 61M | apache-2.0 | 24.1M | 1x MI300X, $1.85/hr |
| all-mpnet-base-v2 | Sentence Transformers | 109M | apache-2.0 | 18.1M | 1x MI300X, $1.85/hr |
| mobilenetv3_small_100.lamb_in1k | PyTorch Image Models | 3M | apache-2.0 | 17.7M | 1x MI300X, $1.85/hr |
| wav2vec2-large-xlsr-53-japanese | Jonatas Grosman | — | apache-2.0 | 16M | — |
| Publisher | Models |
|---|---|
| Team Mradermacher | 164 |
| Qwen | 81 |
| 50 | |
| Quan | 44 |
| RKNNAI | 43 |
| Convergent Intelligence | 39 |
LuminoLex-1.7B is Bangladesh’s first decoder-only language model pretrained from scratch. Built on a sparse Mixture-of-Experts (MoE) architecture, it contains 1.7 billion total parameters while activating only ~410 million parameters per token. By combining an always-on shared expert with Grouped-Query Attention (GQA), LuminoLex-1.7B delivers fast, memory-efficient inference without sacrificing model capacity. This model is released under the Apache License 2.0.
LoRA adapter finetune tu Qwen/Qwen1.5-MoE-A2.7B theo baseline MidAlign, Alternate Training: step chan = task step (LM loss), step le = contrastive align step. (prompt bi mask), tren pool gop cua cac tap: squad, snli, mmlu. - lblosscoef = 0.01, numexperts = 60, topk = 4 tieng Anh va cau target tai layer 12 (block 0-indexed = 11 / 24 layer), temperature = 1.5. task (SQuAD/SNLI/MMLU, English-only) >= 1 lan. Align = pool nho 121571 cap (nguon: flores, ntrex, ted; 500 cap/ngon ngu, boc ngau nhien seed 42), lap lai de du 724736 cap align / epoch (dung nhu paper). - worldsize = 8, alignbatchsize = 16 (per-rank, anchor), taskbatchsize = 16 (per-rank), taskmicrobatchtokens = 4096. - Range layer [8…
static quants of https://huggingface.co/B2J/KorReason-35B-Darwin For a convenient overview and download list, visit our model page for this model. weighted/imatrix quants are available at https://huggingface.co/mradermacher/KorReason-35B-Darwin-i1-GGUF If you are unsure how to use GGUF files, refer to one of TheBloke's READMEs for more details, including on how to concatenate multi-part files. (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) Here is a handy graph by ikawrakow comparing some lower-quality quant And here are Artefact2's thoughts on the matter: https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 See…
Model · Image and text to text
OCP Microscaling FP4 (MXFP4) format via compressed-tensors with dynamic group scaling, optimized for high throughput inference across modern accelerators.
static quants of https://huggingface.co/bingleai/FableOpus-9B-Delta For a convenient overview and download list, visit our model page for this model. weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion. If you are unsure how to use GGUF files, refer to one of TheBloke's READMEs for more details, including on how to concatenate multi-part files. (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) Here is a handy graph by ikawrakow comparing some lower-quality quant…
static quants of https://huggingface.co/racineai/Mistral-Military-24B For a convenient overview and download list, visit our model page for this model. weighted/imatrix quants are available at https://huggingface.co/mradermacher/Berthier-Mistral-Military-24B-i1-GGUF If you are unsure how to use GGUF files, refer to one of TheBloke's READMEs for more details, including on how to concatenate multi-part files. (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) Here is a handy graph by ikawrakow comparing some lower-quality quant And here are Artefact2's thoughts on the matter…
static quants of https://huggingface.co/NadevA23/Kronumos For a convenient overview and download list, visit our model page for this model. weighted/imatrix quants are available at https://huggingface.co/mradermacher/Kronumos-i1-GGUF If you are unsure how to use GGUF files, refer to one of TheBloke's READMEs for more details, including on how to concatenate multi-part files. (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) Here is a handy graph by ikawrakow comparing some lower-quality quant And here are Artefact2's thoughts on the matter: https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 See…
static quants of https://huggingface.co/DJLougen/Ornstein-27B For a convenient overview and download list, visit our model page for this model. weighted/imatrix quants are available at https://huggingface.co/mradermacher/Ornstein-27B-i1-GGUF If you are unsure how to use GGUF files, refer to one of TheBloke's READMEs for more details, including on how to concatenate multi-part files. (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) Here is a handy graph by ikawrakow comparing some lower-quality quant And here are Artefact2's thoughts on the matter: https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 See…
中文概率决策模型的 GGUF 版本：llama.cpp 推理，CPU 即可部署 各尺寸、部署格式与外部模型对比。2B BF16 与 2B Q80 均已公开发布并完成 CJ-Bench 全量评测：2B 整体准确率更高，0.8B 更小更快，部分法律判断与金融评分任务仍是 0.8B 更好。 本仓库是 Chinese Decision 0.8B 的 GGUF 格式导出，用于 llama.cpp / llama-cpp-python 推理。 原版模型是一个中文决策模型：给定上下文和一组固定候选项（单题 2–26 个；类别更多的 choice 问题可用服务端的 /v1/tournament 分组淘汰），一次前向直接返回每个候选项的概率，不生成任何 token。支持 noul（是/否）、choice（单选）、score（有序等级）三种题型，覆盖通用、医疗、法律、金融四个领域。模型能力、训练细节与应用案例见原版模型卡。 GGUF 版本的特点： - 无需 PyTorch 和 GPU：llama-cpp-python 即可在 CPU 上运行，也可用 CUDA 版 llama.cpp 跑在 GPU 上。 - 体积约为原版的一半：Q80 为 812 MB，原版 safetensors 为 1.50 GB。 - 内存占用更低：同一台服务器上，CPU 推理进程峰值内存 2.19 GiB，Transformers FP32 为 7.44 GiB。 - 精度基本不变：CJ-Bench 全量 307,900 条上，准确率、NLL、ECE、Brier 的变化都在千分之一以内。…
static quants of https://huggingface.co/bingleai/FableOpus-9B-Linear For a convenient overview and download list, visit our model page for this model. weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion. If you are unsure how to use GGUF files, refer to one of TheBloke's READMEs for more details, including on how to concatenate multi-part files. (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) Here is a handy graph by ikawrakow comparing some lower-quality…
Image and text on Rockchip RK3576 and RK3588, converted from Qwen/Qwen3.5-2B. Use the files for your board’s exact SoC. w4a16 uses 4-bit weights and 16-bit activations; w4a16g128 adds a weight group size of 128. w8a8 uses 8-bit weights and activations. File size below is download size, not total runtime RAM. For image input, also download the vision encoder for the same SoC. Keep the language model and vision encoder from this release together. ONNX files are export intermediates; they are not needed to run these RKNN/RKLLM models. With Docker installed on a matching Rockchip board, this example starts the RK3576 w4a16g128 model and its API on port 8001: The image includes its model files.…
Solstice-AI/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NM-DAU-mlx-oQ8e is the native 262K context Apple Silicon mixed-precision serving release of DavidAU's flagship Qwen3.8-27B Cold Fusion foundation (DavidAU/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NM-DAU). Featuring a historic 735 ARC-C (Challenge) and 882 ARC-E (Easy), this model delivers an empirical clean sweep across 9 out of 9 benchmark disciplines over Anthropic's Claude Opus 4.6 Max under the official Claude Code evaluation harness. Engineered with native 262,144 Token (262K Token) context, calibrated via importance matrix optimization (oqimatrixreport.json), and accelerated natively by…
PMA-1.2 is Patriot Memory's 127.9M-parameter on-device language model. It speaks English and Traditional Chinese, answers as PMA from Patriot Memory, and fits in a 128 MB parameter budget built for edge hardware. It is a new architecture, a new tokenizer, and an order of magnitude more training, aimed at the same job: a small, fast, honest assistant for Patriot Memory and Viper Gaming questions and general chat. It provides accurate information regarding: If you run into multi-GPU tensor device mismatch errors: Run the script with CUDAVISIBLEDEVICES=0 to isolate execution to GPU 0. trustremotecode=True is required: PMA-1.2's architecture is our own and ships as small Python files next to…
static quants of https://huggingface.co/emonHasan01/Bangla-Gemma-Pro For a convenient overview and download list, visit our model page for this model. weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion. If you are unsure how to use GGUF files, refer to one of TheBloke's READMEs for more details, including on how to concatenate multi-part files. (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) Here is a handy graph by ikawrakow comparing some lower-quality…
Official VAL-APEX-I quantization of huihui-ai/Huihui-Qwen3.8-27B-abliterated. Vector-calibrated Asymmetric Layer-wise Outlier-preserving Recurrent-aware Unified Matrix-quantization The NanoPlus V3 file is 11.35 GB, approximately 0.45 GB smaller than GSQ-RCO IQ3S, with 11.49% lower reported WikiText-2 PPL (6.2577 vs 7.07). MiniPlus V3 reaches 13.21% lower reported PPL (6.1361 vs 7.07) at 14.16 GB, approximately 2.36 GB larger. × is the number of tensors in each format. Counts were read from the released GGUF headers; the GSQ-RCO column uses its published tensor allocation. This release contains 866 tensors. The main GGUF includes the additional 15-tensor MTP head. The model supports a native…
For dispute adjudication, use the full-precision model until the higher-precision GGUF builds are here. Apache 2.0
Official VAL-APEX-I quantization of huihui-ai/Huihui-Qwen3.8-27B-abliterated. Vector-calibrated Asymmetric Layer-wise Outlier-preserving Recurrent-aware Unified Matrix-quantization The NanoPlus V3 file is 11.35 GB, approximately 0.45 GB smaller than GSQ-RCO IQ3S, with 11.49% lower reported WikiText-2 PPL (6.2577 vs 7.07). MiniPlus V3 reaches 13.21% lower reported PPL (6.1361 vs 7.07) at 14.16 GB, approximately 2.36 GB larger. × is the number of tensors in each format. Counts were read from the released GGUF headers; the GSQ-RCO column uses its published tensor allocation. This release contains 866 tensors. The main GGUF includes the additional 15-tensor MTP head. The model supports a native…
static quants of https://huggingface.co/prithivMLmods/Qwen3.5-35B-A3B-abliterated-v2-MAX For a convenient overview and download list, visit our model page for this model. weighted/imatrix quants are available at https://huggingface.co/mradermacher/Qwen3.5-35B-A3B-abliterated-v2-MAX-i1-GGUF If you are unsure how to use GGUF files, refer to one of TheBloke's READMEs for more details, including on how to concatenate multi-part files. (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) Here is a handy graph by ikawrakow comparing some lower-quality quant And here are Artefact2's thoughts on the matter…
Text generation on Rockchip RK3576 and RK3588, converted from Qwen/Qwen2.5-3B-Instruct. Use the files for your board’s exact SoC. w4a16 uses 4-bit weights and 16-bit activations; w4a16g128 adds a weight group size of 128. w8a8 uses 8-bit weights and activations. File size below is download size, not total runtime RAM. With Docker installed on a matching Rockchip board, this example starts the RK3576 w4a16 model and its API on port 8001: The image includes its model file. See rkllm-docker for API requests, other board variants, and configuration. To download the files separately instead: These are native RKLLM/RKNN artifacts. Use a compatible RKLLM runtime and the model’s correct chat…
Model · Image and text to text
Solstice-AI/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NM-DAU-mlx-oQ6e-1M is the sweet-spot Apple Silicon mixed-precision serving release of DavidAU's flagship Qwen3.8-27B Cold Fusion foundation (DavidAU/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NM-DAU). Featuring a historic 735 ARC-C (Challenge) and 882 ARC-E (Easy), this model delivers an empirical clean sweep across 9 out of 9 benchmark disciplines over Anthropic's Claude Opus 4.6 Max under the official Claude Code evaluation harness. Engineered with baked-in 1,048,576 Token (1 Million Token) YaRN RoPE scaling, calibrated via importance matrix optimization (oqimatrixreport.json), and accelerated…
static quants of https://huggingface.co/simonko912/simllama-1.1-instruct-beta For a convenient overview and download list, visit our model page for this model. weighted/imatrix quants are available at https://huggingface.co/mradermacher/simllama-1.1-instruct-beta-i1-GGUF If you are unsure how to use GGUF files, refer to one of TheBloke's READMEs for more details, including on how to concatenate multi-part files. (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) Here is a handy graph by ikawrakow comparing some lower-quality quant And here are Artefact2's thoughts on the matter…
This is a Qwen3.5-4B-Base model fine-tuned on BIRD using EliteReplay. EliteReplay combines reinforcement learning with supervised replay from an archive of verified, diverse SQL solutions to preserve solution diversity during training. We train on 5,000 BIRD questions. Archive search uses 1,000 of those questions to select 1,500 verified SQL examples for replay. The model uses GRPO with supervised archive replay at weight μ = 0.05. Hyperparameters and implementation details are available in the training instructions, original training configuration, and checkpoint metadata. Training used 4 NVIDIA A100 80 GB GPUs, with two for policy optimization and two for rollout generation, using veRL…
Welcome to APEX-I-MiniPlus-V2.1 for t-tech/T-Search (the specialized 35B Mixture-of-Experts architecture developed by t-tech as an agentic retriever that plans, executes multi-round searches, and synthesizes verifiable evidence chains). Standard automated community quantizations uniformly degrade sensitive routing matrices and expert feed-forwards down to 2-bit codebooks, corrupting retrieval planning trajectories, hallucinating query filters, and dropping critical visual tokens. APEX-I-MiniPlus-V2.1 was engineered differently. This is a 100% custom, hand-crafted tensor-by-tensor quantization built with mathematical precision overrides, calibrated importance matrices (imatrix), and an…
If this model is useful to you, support the work by following @nawariokra on X. Qwen/Qwen3.8-Flash-Next (125B MoE, 6B active) on one 24 GB GPU plus CPU, with the full 262,144-token context. Two GGUF shards: 47.5 GiB of weights and a 48.3 GiB n-gram table (95.8 GiB in all). It runs on our own engine TRUSS. Stock llama.cpp cannot read this file. It needs TRUSS. See Requirements and SERVING.md. Example scenes made with this model: web pages it wrote, screen-recorded in a browser. Watermelon jelly (WebGPU) Rocket launch scene Paris nocturne (voxel garden with fireworks) Flash-Next carries a 51.2-billion-parameter n-gram embedding table. It is most of the file, and it is not loaded into GPU or…
Community GGUF quantizations of empero-ai/Qwen3.8-35B-A3B-Distill. If this GGUF made your day easier, a coffee would make mine. I build and test these releases myself. Your coffee helps keep me going. Thank you for supporting this work. This release is based on the upstream Qwen3.8-35B-A3B-Distill model card. The model is a text-generation MoE model with 35B total parameters and approximately 3B active parameters per token, using 256 experts with 8 routed experts. It uses hybrid attention components and has a native context length of 262,144 tokens in the upstream configuration. The GGUF files are intended for local inference with llama.cpp and compatible runtimes. The upstream model card…
Architecture: Qwen 3.6 35B-A3B (MoE) | Total Params: ~34.7B | Active Params: ~3B | Context: 262,144 native / 1,010,000 extensible | Base: Heretic (llmfan46) | Teacher: Claude Fable 5 | Type: Distilled + Abliterated MoE LLM A personal fork of llmfan46/Qwen3.6-35B-A3B-uncensored-heretic — an uncensored Heretic-style abliteration of Qwen/Qwen3.6-35B-A3B, the 35B-total / 3B-active mixture-of-experts multimodal base — repackaged as Janus-35B with Claude Fable 5 reasoning data in the teacher slot. Refusal-trained behavior is dialed back at the base layer. One-liner via Hugging Face (pulls a GGUF + this repo's root-level template / system / params files, including the tool-calling template — HF's…
We are excited to release the XiYanSQL-QwenCoder-2504 version, our latest SQL generation model. This version continues to optimize upon the previous version, delivering enhanced performance. - Our model incorporates important explorations combining fine-tuning and GRPO training, leveraging the post-training strategies of GRPO without a thinking process, achieving both efficiency and accuracy in SQL generation. - It demonstrates impressive performance and supports multiple dialects, ready to use out of the box. - Improved generalization capabilities, excelling on different dialects and out-of-domain datasets. In this evaluation, we have also added a real-world SQL benchmark (the DW test…
This model is a merge of: - nightmedia/Qwen3.6-35B-A3B-Brainwaves - orcarouter/Nex-N2.5-mini-Uncensored - thomsonreuters/Thomson-1.0-Small - nightmedia/Qwen3.6-35B-A3B-Fable-Holo3.1 - nightmedia/Qwen3.6-35B-A3B-FSM - orcarouter/Nex-N2.5-mini-Uncensored Lab name: Qwen3.6-35B-A3B-AgentWorld-Fable-Holo3.1-Iris-Thomson-B-Nex2 Brainwaves Performance with different expert count (more metrics coming) Qwen3.6-35B-A3B-Brainwaves orcarouter/Nex-N2.5-mini-Uncensored The merge with the original nex-agi/Nex-N2.5-mini Qwen3.6-35B-A3B-Brainwaves-Nex nex-agi/Nex-N2.5-mini Qwen3.6-35B-A3B-Instruct This model is using(an early version of) the fixed jinja template from froggeric/Qwen-Fixed-Chat-Templates Drop…
Fully on-device, multilingual text-to-speech in a single file. This is hexgrad/Kokoro-82M (82M-parameter StyleTTS 2 + ISTFTNet) packaged as a.litertlm bundle for LiteRT-LM, Google's open-source on-device inference runtime. Everything needed to turn text into 24 kHz speech is inside the one file: INT8 acoustic + vocoder models, all 54 voices, and self-contained text front-ends (text normalization and grapheme-to-phoneme) for 9 languages / dialects — no Python, no network, and no espeak-ng, so the whole stack is Apache-2.0. The fp16 files contain the same acoustic model weights, voices and text front-ends as the originals, so their CPU output and pronunciation are the same. Within each…
Text generation on Rockchip RK3576 and RK3588, converted from Qwen/Qwen2.5-1.5B-Instruct. Use the files for your board’s exact SoC. w4a16 uses 4-bit weights and 16-bit activations; w4a16g128 adds a weight group size of 128. w8a8 uses 8-bit weights and activations. File size below is download size, not total runtime RAM. With Docker installed on a matching Rockchip board, this example starts the RK3576 w4a16 model and its API on port 8001: The image includes its model file. See rkllm-docker for API requests, other board variants, and configuration. To download the files separately instead: These are native RKLLM/RKNN artifacts. Use a compatible RKLLM runtime and the model’s correct chat…
Observed sparse-MMA microbenchmark peak on this Vast GB10: 992.018 TFLOP/s dense-equivalent, 99.20% of the 1 PFLOP/s target A ~2B-parameter language-model architecture designed around NVIDIA GB10 / SM121 sparse NVFP4 from the start, rather than retrofitting a generic Transformer. - 1,990,038,784 conventional parameters (0.498% below the 2B design target) - 600,000,000,000 training-token target (~302 tokens/parameter) - 16 sequential stages - 6 top-1 experts per stage, 96 experts total - model width 1280 - every expert uses 1280 -> 5120 -> 1280 SwiGLU - expert matrices are paired 4:8 structured sparse NVFP4 - native packed mxf4nvf4 SM121 sparse MMA is the target hot path - 20 query heads / 5…
static quants of https://huggingface.co/prithivMLmods/Qwen3.6-27B-Uncensored-Aggressive For a convenient overview and download list, visit our model page for this model. weighted/imatrix quants are available at https://huggingface.co/mradermacher/Qwen3.6-27B-Uncensored-Aggressive-i1-GGUF If you are unsure how to use GGUF files, refer to one of TheBloke's READMEs for more details, including on how to concatenate multi-part files. (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) Here is a handy graph by ikawrakow comparing some lower-quality quant And here are Artefact2's thoughts on the matter…
A 4-bit quantized, business-focused conversational AI built on Mistral 7B using Unsloth. Optimized for low VRAM (runs on 6GB+ VRAM) and for Indian business use-cases. - 7B params in 4-bit (BF16 base): ~4GB RAM me chal jayega from unsloth import FastLanguageModel model, tokenizer = FastLanguageModel.frompretrained( modelname = "UX4567/Khushi-Business-AI-4bit", maxseqlength = 2048, loadin4bit = True, prompt = "Ek customer bol raha hai: Mujhe refund chahiye, kya reply du?" inputs = tokenizer([prompt], returntensors = "pt").to("cuda") outputs = model.generate(inputs, maxnewtokens = 200) print(tokenizer.batchdecode(outputs)[0])
Stanza is a collection of accurate and efficient tools for the linguistic analysis of many human languages. Starting from raw text to syntactic analysis and entity recognition, Stanza brings state-of-the-art NLP models to languages of your choosing. Find more about it in our website and our GitHub repository. This card and repo were automatically prepared with huggingstanza.py in the stanfordnlp/huggingface-models repo
ViDense is a VietNamese Embedding Model. Fine-tuned and enhanced with tailored methods, ViDense incorporates advanced techniques to optimize performance for text embeddings in various applications. Trained for 10 epochs with a train batch size of 2048. Utilizes a 3-phase training approach, where the best checkpoint from each phase serves as the base model for the next. Momentum Encoder: Incorporates MoCo (Momentum Contrast) to enhance in-batch negative sampling. of positives as relevant to the anchor, it reranks the corpus using the Spearman metric and integrates Spearman weights into the loss calculation for improved ranking. Below is a comparision table of the results I achieved compared…
pipelinetag: any-to-any
This qwen2 model was trained 2x faster with Unsloth and Huggingface's TRL library.
Conventional diffusion and autoregressive pixel/patch video generators spend 99% of their compute budget denoising millions of redundant pixel patches frame by frame. Vivy-R-Vision-3B (R-VISION-3B) replaces brute-force pixel diffusion with a Two-Stage Hybrid Architecture: 1. Stage A — The 3.09B LLM Arrangement Compiler (3% Compute Share, vivy-r-vision-3b-q4km.gguf &.safetensors): - A complete 3,085,938,688-parameter (3.09B) 36-layer Transformer model (dmodel = 2048, 435 tensors) fine-tuned via 36-layer BitFit (attnq.bias, attnk.bias, attnv.bias) and RMSNorm-IA³ (attnnorm.weight, ffnnorm.weight, outputnorm.weight) together with a multi-head dmodel = 2048 Semantic Projection Compiler.…
static quants of https://huggingface.co/ValiantLabs/Qwen3-14B-Cobalt2 For a convenient overview and download list, visit our model page for this model. weighted/imatrix quants are available at https://huggingface.co/mradermacher/Qwen3-14B-Cobalt2-i1-GGUF If you are unsure how to use GGUF files, refer to one of TheBloke's READMEs for more details, including on how to concatenate multi-part files. (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) Here is a handy graph by ikawrakow comparing some lower-quality quant And here are Artefact2's thoughts on the matter: https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 See…
High-efficiency, hardware-benchmarked GGUF releases of DeepSeek-V4.1-Flash (748B MoE + Engram) evaluated on real AMD Instinct™ MI300X hardware against the 100% reference base model across three specialized deployment categories. 748.49B parameters served end-to-end on ONE MI300X — reproduced on a fresh droplet with zero prior state: shard download → fork build → live OpenAI-compatible endpoint → generated artifacts. All measurements from the server's own timings blocks. Generated artifacts — shipped in artifacts/ as proof-of-work: Raw run data (benchmark JSON + server log): evidence/run20261005/ These GGUFs declare general.architecture = deepseek41, which exists only in the…
This is an uncensored research model. Its built-in refusals were removed, so it answers prompts the base model declines, including chemical and biological synthesis, cybercrime, weapons, harassment, and fraud. Use it for red-teaming, offensive-security research, and refusal-rate evaluation. It has no guardrails of its own: if you deploy it, add your own input and output moderation (for example Llama Guard). Abliterated variant of prism-ml/Ternary-Bonsai-2-27B-gguf (PrismML's ternary compression of Qwen/Qwen3.8-27B, 27B hybrid attention + GatedDeltaNet). The refusal direction was removed with runtime projective steering (GLP, the weightless method behind the Inkling steering vectors)…
Solstice-AI/Qwen3.8-27B-TTURBO-Cold-Fusion-709-L-Uncensored-mlx-oQ4e is the official Apple Silicon MLX release of DavidAU's Qwen3.8-27B-TWIN-TURBO-Fable-Cold-Fusion-709-L-Uncensored. Engineered specifically for Apple Silicon Unified Memory architectures (M2, M3, M4, M5 Max / Ultra), this release couples oQ4e imatrix-guided mixed-precision with Solstice's proprietary 10-Level Cognitive Variable Thinking System and native Hardware Multi-Token Prediction (MTP). This checkpoint embeds the Solstice 10-Level Cognitive Jinja chat template, allowing instant dynamic control over reasoning depth
static quants of https://huggingface.co/bingleai/FableOpus-9B-TIES For a convenient overview and download list, visit our model page for this model. weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion. If you are unsure how to use GGUF files, refer to one of TheBloke's READMEs for more details, including on how to concatenate multi-part files. (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) Here is a handy graph by ikawrakow comparing some lower-quality quant…
llamapi run handles model download, loading, and execution. See the LlamaPi Wiki for setup and usage. Gemma 4 E2B IT is a compact instruction-tuned multimodal model developed by Google DeepMind. - Accepts text, image, and audio inputs and generates text output with an encoder-free unified architecture. - Supports reasoning, coding, multilingual, and agentic tasks with a 256K context window and 140+ languages. - Designed as an efficient open model for on-device and edge deployment. The models provided in this repository are converted and adapted by the Firefly AI team from the original models. All intellectual property rights and copyright in the underlying original models remain with the…
static quants of https://huggingface.co/RinggAI/Transcript-Analytics-Qwen3.5-0.8B For a convenient overview and download list, visit our model page for this model. weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion. If you are unsure how to use GGUF files, refer to one of TheBloke's READMEs for more details, including on how to concatenate multi-part files. (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) Here is a handy graph by ikawrakow comparing some…
static quants of https://huggingface.co/udgamlabs/Udgam-384M-Base For a convenient overview and download list, visit our model page for this model. weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion. If you are unsure how to use GGUF files, refer to one of TheBloke's READMEs for more details, including on how to concatenate multi-part files. (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) Here is a handy graph by ikawrakow comparing some lower-quality quant…
static quants of https://huggingface.co/udgamlabs/Udgam-384M-Base-4K For a convenient overview and download list, visit our model page for this model. weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion. If you are unsure how to use GGUF files, refer to one of TheBloke's READMEs for more details, including on how to concatenate multi-part files. (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) Here is a handy graph by ikawrakow comparing some lower-quality…
static quants of https://huggingface.co/udgamlabs/Udgam-384M-Chat For a convenient overview and download list, visit our model page for this model. weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion. If you are unsure how to use GGUF files, refer to one of TheBloke's READMEs for more details, including on how to concatenate multi-part files. (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) Here is a handy graph by ikawrakow comparing some lower-quality quant…
static quants of https://huggingface.co/ElementMerc/tinyllama-1.1b-abliterated For a convenient overview and download list, visit our model page for this model. weighted/imatrix quants are available at https://huggingface.co/mradermacher/tinyllama-1.1b-abliterated-i1-GGUF If you are unsure how to use GGUF files, refer to one of TheBloke's READMEs for more details, including on how to concatenate multi-part files. (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) Here is a handy graph by ikawrakow comparing some lower-quality quant And here are Artefact2's thoughts on the matter…
This repository contains one current checkpoint of the serial old/new Sparse-AST family for byte-level Blender Python completion. It was recovered from results (4).zip, the newest relevant training-results archive found in the local Downloads search, and its saved training state confirms step 93,213. It continues from step 90,213 through 3,000 successful updates, with no recorded non-finite skips. Updated 16 October 2026. The current release is under latest/ and uses SafeTensors for model weights and training-state tensors. That release contains no.pt checkpoints. Existing remote variant folders are retained as historical artifacts; they are not the latest checkpoint. The pre-update legacy…
The smallest and first model from CyanoAI — a 190.5M-parameter dense English base LM. Named after Prochlorococcus, the tiniest and most oxygen-producing photosynthetic organism on Earth: small, dense, and outproducing everything its size. All variants share the same architecture, tokenizer, and vocabulary, so they are drop-in interchangeable. Training corpus: a curated ~826GB English mixture (web / books / code / reference), stream-packed with the tokenizer jointly shipped in this repo. This is a base model — it speaks fluent Wikipedia-style prose but has not been aligned. For chat or assistant behaviour, start from the SFT or aligned variants. Zero-shot on wikitext (JSON subset, ~500k…
static quants of https://huggingface.co/Iknow5/YoutuberGPT For a convenient overview and download list, visit our model page for this model. weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion. If you are unsure how to use GGUF files, refer to one of TheBloke's READMEs for more details, including on how to concatenate multi-part files. (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) Here is a handy graph by ikawrakow comparing some lower-quality quant And here…
static quants of https://huggingface.co/wowbager/granite-cermat-cz-7b For a convenient overview and download list, visit our model page for this model. weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion. If you are unsure how to use GGUF files, refer to one of TheBloke's READMEs for more details, including on how to concatenate multi-part files. (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) Here is a handy graph by ikawrakow comparing some lower-quality…
A four-way omnimergev2 merge over Qwen/Qwen3.5-9B, built for one job: multi-turn agentic coding — staying on a task across turns and tool calls until it is actually finished. It is not built to win knowledge benchmarks, and its world knowledge is limited for its size. What it is built to do is finish, and stop. --base and --task-base are both Qwen3.5-9B: every source descends from it, so task vectors are taken against the true common ancestor instead of against a sibling. merge (--skip-patterns visual.,mtp.) and passed through, so the draft head survives — an averaged MTP head stops being a usable drafter. There is no vision tower. config.json inherits a populated visionconfig from the…
Solstice-AI/Qwopus3.8-27B-Flash-mlx-oQ4e-1M provides the official, production-grade Apple Silicon MLX (oQ4e) release of Qwopus3.8-27B-Flash with a native-behaving 1,048,576-token (1M) context window. Official Apple Silicon MLX oQ4e mixed-precision release tailored for macOS unified memory execution with native-behaving 1M context. Evaluated under the standardized benchmark harness: 1M YaRN Scaling & Quantization Suite: Solstice-AI
static quants of https://huggingface.co/RinggAI/Transcript-Analytics-Qwen3.5-2B For a convenient overview and download list, visit our model page for this model. weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion. If you are unsure how to use GGUF files, refer to one of TheBloke's READMEs for more details, including on how to concatenate multi-part files. (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) Here is a handy graph by ikawrakow comparing some…
A binary attack-vs-benign detector for blockchain-node network/resource attacks, trained entirely on faithful reproductions of publicly-disclosed attacks. Every attack class in the corpus reproduces a specific public disclosure — a CVE, a GHSA, or a named third-party security audit — and each carries a provenance.sourceclass recording how public its sourcing is. Part of NullRabbit's work on autonomous defence for decentralised networks — watch the outside of the perimeter. Given the network-layer signal of a short capture window against a blockchain node (packet-rate / size statistics from the pcap, and amplification / request-response / timing statistics from the RPC responses), the model…
GGUF builds of Jebadiah 27B for llama.cpp, which runs on NVIDIA, AMD and Apple GPUs and on plain CPUs. Jebadiah answers a typed question (choice, noul or score) with a probability for every option, read from one forward pass. Nothing is generated. Code, trainer and evals: Results and docs - Project site, with every result and how to run the models: jebadiah.ai. - Decision Index 0.2.1: Jebadiah 27B scores 54.67, #5 of 67 open models (as of 2026-09-26). This is the board's own number; the maintainer validated my run and put it on the leaderboard. Run record. Which one should I use? For local use, start with Jebadiah 9B v2 GGUF. On Apple silicon, use an MLX build: 27B, 9B v2 or 4B v2. For vLLM…
GGUF builds of Jebadiah 9B v2 for llama.cpp, which runs on NVIDIA, AMD and Apple GPUs and on plain CPUs. Jebadiah answers a typed question (choice, noul or score) with a probability for every option, read from one forward pass. Nothing is generated. Code, trainer and evals: Results and docs - Project site, with every result and how to run the models: jebadiah.ai. - JDE blind test (as of 2026-09-26): on 290 real decisions from Titanium Computing's production decision engine, Jebadiah 9B v2 got 277 against Jev's 282, with 0 flips across 5,800 repeat calls. Jev still leads on coverage checks. Which one should I use? For local use, start with Jebadiah 9B v2 GGUF. On Apple silicon, use an MLX…
Yes. The Apache License 2.0 is a permissive open-source license. It permits commercial use, modification and redistribution. It requires keeping the license and copyright notices and any NOTICE file, stating significant changes, and it includes an express patent grant from contributors.
By monthly downloads reported by the Hugging Face Hub: LuminoLex-1.7B (564); Qwen1.5-MoE-A2.7B-MidAlign (560); KorReason-35B-Darwin-GGUF (558).
