static quants of https://huggingface.co/olaverse/PurpleMIST-Mini-1.0
SAVRN Model Hub
Open-Weight Models
An open-weight model is an AI model whose trained weights are published for anyone to download. The weights are what the model learned in training. With a copy of them you can run the model on hardware you control and train it further on your own data.
Open weights are not the same as open source. Many publishers release the weights without the training data or code, and the license sets what you may do with the model. This library puts each model's full card, architecture, files, license and published evaluations on one page.
12,579Models
3,583Datasets
291Papers
7,578Publishers
12,850Sourced relationships
Updated 2026-10-23 · How the library is built
12,579 models, sorted by most downloaded.
Pyrut-8B-Instruct-Uncensored is a high-performance, uncensored coding assistant optimized for complex software engineering tasks, agentic workflows, and function calling. Download from ImposterOnline/Pyrut-8B-Instruct-Uncensored-GGUF. Pyrut is a private, independent project for high-performance, uncensored engineering assistance.
Quantized builds for Pyrut-8B-Instruct-Uncensored.
This release contains the main Stage-0 direct scorers and Stage-1 reasoning-context checkpoints used in the Q-Scorer+ pipeline. The checkpoints are compact Q-Scorer+ checkpoints: they contain LoRA adapters, the score head, the score-token delta, tokenizer files, and reports. They are not merged 8B weight dumps. The base model is fetched from Qwen/Qwen3-VL-8B-Instruct. Clone this repository together with the repository root, or copy qscorerplus/ to your Python path. Then load a checkpoint with: The loader resolves the base model from Qwen/Qwen3-VL-8B-Instruct. No local base-model files are required as long as HuggingFace Hub is reachable. For offline use, download the base model first and…
新配置由 python3 -u tools/runcorrectedqojtraining.py 启动， 先完成 96 局历史/48 局 PPO 的流程对照，再自动启动全量运行。 输出 runs/resnet-guarded-20261004，旁侧.job.json 记录阶段和进程，.log 记录实时训练进度。恢复正式训练使用同一命令追加 --resume。 - 从上一轮 best.pt 保留宽度 256、两路各 4 层的共享表示，切换冻结先验为 指定 ResNet best；重置四个残差策略头和门控，使新起点的出牌/叫分 argmax - 关闭历史动作模仿 (--history-weight 0) 及历史终局收益对价值/胜负头的监督。 历史公共状态用于 ResNet 的动作蒸馏、KL 和真实暗牌标签辅助训练； 价值头使用实际生成的教师轨迹和新鲜 PPO 轨迹。 PPO 从验证 best.pt 开始，学习率 5e-6，教师 KL 权重.15，每轮 96 局、1 轮更新。 - 通常 75% 对局直接针对目标 ResNet，剩余为自博弈和快照。快照随机选择， - 更新后计算整轮所有状态、全部合法动作上的精确 old||new KL。 - 正式预算 256 轮，共 24,576 局 PPO；最终测试另保留 256 副发牌/3,072 局， 并用独立 JavaScript 规则回放。新训练/验证/测试种子区间均避开旧实验。 强先验检查点使用格式 2，记录 teachermodeltype 和权重哈希，加载时自动选择 ResNet best；旧格式 1 的 LSTM…
Fine-tuned Qwen Image 2.1 autoencoder for RGBA / HDR-oriented reconstruction. The goal is stronger dynamic range, color volume, and detail energy for HDR-style workflows—not perfect fidelity to the source frame. Relative to ground truth and compared with base Qwen 2.1 VAE (VAE A): VAE B deliberately overshoots GT on Lab color volume, edge density, and gradient energy. VAE A stays closer to GT on SSIM/PSNR but compresses color volume and softens detail. That tradeoff is the point of this checkpoint. - Uses the VAE’s own latentsmean / latentsstd (no FLUX/SD 0.18215 scaling) - Trained / evaluated around 512–1024 resolution; spatial size should be divisible by 16 - HDR-oriented encode/decode in…
Qev-2B is the compact member of the Qev decision-model family. It learns option probabilities and representation responses from Qev-9B, and supports Choice, Noul and Score with the same request format. Install Qev from the source repository using Python 3.12 and a hardware-compatible PyTorch 2.8.0 build. The loader downloads this adaptation package and the compatible Qwen base separately. The teacher is not needed for inference. Use revision="v0.1.0" to select the first published release. To fine-tune on your own data, use configs/qev-2b-finetune.json with python -m qev.train --init-checkpoint AustinFu/Qev-2B. To train with a teacher, follow the distillation guide or 中文指南. Accuracy (%).…
Qev fine-tunes Qwen into a decision model. Give it context, a question, and answer options; receive a decision and a probability for each option. One model supports Choice, Noul (yes/no), and Score (ordered ratings). Qev-9B combines a general decision-training dataset with additional alignment and rule-compliance examples, repeated three times during the second half of training. It uses the full candidate-interaction architecture shown below. Use Python 3.12 and install a hardware-compatible PyTorch 2.8.0 build, then install Qev from its source repository: The Qev loader downloads this checkpoint and the pinned Qwen base separately. Use the Qev Python or JSONL interface to load the adapter…
static quants of https://huggingface.co/purav-raj321/Quantrexa-Prime-1.5B 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 LoRA adapter for Qwen/Qwen3-4B — the in-context reader of the Quorum 24-shot intent-classification ensemble. Given 24 retrieved examples in the prompt (no weight update), it scores every candidate label in a single forward pass. Combined (geometric mean) with a frozen BAAI/bge-large-en-v1.5 nearest-neighbour over the same 24 examples, the ensemble reaches 0.932 on Banking77 (full 3,080 test) — above the closed API Jev's 0.924 at Jev's own 24-shot protocol. In our study a further configuration (per-class descriptions + a calibration-selected combination) reached 0.938 and significantly beat Jev on a paired McNemar test LoRA (r = 64) on Qwen/Qwen3-4B, fine-tuned on a mixture of public…
Research checkpoints: Qwen/Qwen2.5-7B-Instruct fully fine-tuned on the ToolUse task with SFT or SDFT, on clean demonstrations or with 20% of demonstrations deliberately mismatched to other questions (mm20). Only the seed-42 final checkpoint of each of the 4 configurations is published; each lives in its own subfolder with a model card, sha256 list and eval results. mismatch models were trained on intentionally corrupted data and are for research only. PROTOCOL.md is the locked experiment protocol. manifests/ holds the train/val split (record ids) and the corruption mapping (record indices + hashes; no dataset text).
A high-throughput inference engine for structured information extraction, decision routing, and categorical classification on Apple Silicon using MLX. Parallel Constrained Decoding evaluates multi-field JSON schemas simultaneously rather than generating tokens sequentially. On an Apple Silicon M4 Max, it delivers 5.6x to 7.0x latency reductions compared to standard autoregressive decoding with 100% schema validity and calibrated field-level confidence scores. Evaluated with mlx-community/Qwen2.5-1.5B-Instruct-4bit on macOS Sequoia: Standard LLM structured generation (such as JSON mode or grammar-guided sampling) relies on token-by-token autoregressive decoding: Each token requires a…
An adult (18+) Chinese roleplay LoRA for JoyFox-Qwen3.6-35B-A3B-RP-Aggressive. This repository contains the run-3 adapter, which met the explicit-density target. 面向成人（18+）中文角色扮演的 LoRA 适配器，基座为 JoyFox-Qwen3.6-35B-A3B-RP-Aggressive。 监督 token（1.33%）来自「幼龄角色参与性行为」的文本，约 5–7 篇不同源文（同一文本被渲染成 A LoRA (not a merged model). Target modules: qproj, kproj, vproj, oproj, inprojqkv, inprojz, outproj — rank 16, alpha 32, dropout 0.05, bf16 base, 14.25 M trainable parameters across 130 modules. Trained with response-only loss masking over a 384-token sliding window, on a packed corpus of Chinese roleplay turns. Chinese-language adult roleplay, single-user, local inference. Per-turn prose of roughly 800–1000…
This is an OpenVINO INT4 quantized version of empero-ai/Qwen3.8-9B-Distill, generated using optimum-intel. For detailed specifications, evaluation scores, and architecture info, please refer to the original repository: empero-ai/Qwen3.8-9B-Distill.
Model Collections
Hand-picked starting points, each with the reason it exists.
Collection · 4 entries
Embedding models for retrieval
Sentence and document embedding models used to build retrieval systems. Dimension and sequence length matter more than size here, and both come from the publisher.
Collection · 4 entries
Models that fit on one accelerator
Models whose publisher-reported parameter count puts them within reach of a single accelerator at common precisions. Memory needed depends on precision and serving configuration, so treat the parameter count as the starting point, not the answer.
Collection · 6 entries
Open-weight text models worth knowing
Widely used open-weight language models, chosen because each one is a distinct family rather than a variant of the one above it. Selection, not a ranking.
Collection · 3 entries
Speech and audio models
Recognition and synthesis models, grouped so the two directions are easy to compare.
Open-Weight Models Explained
What is an open-weight model?
An AI model whose trained weights are published for anyone to download, so it can be run, tested and fine-tuned on hardware the user controls.
Is an open-weight model the same as open source?
Not always. Open weights means the trained model can be downloaded. Open source usually also means the training code and data are available and the license allows broad reuse. Many open-weight models release the weights only.
Can I use an open-weight model commercially?
It depends on the license. Apache 2.0 and MIT allow commercial use. Other licenses limit it, for example to non-commercial use or below a set number of users. Every model page here shows its license.
How much memory does an open-weight model need?
About two bytes per parameter at 16-bit precision, so a 7-billion-parameter model needs roughly 14 GB for its weights, plus memory for the context it processes. Each model page lists its parameter count and the size of its files.
Related SAVRN Research
The hub sits beside SAVRN's market data and infrastructure research: what models cost to run, and what it takes to run them.
SAVRN Index
What open models cost to run
The same open-weight model priced by every host that serves it, per million tokens.
Research Hub
Data center trackers and maps
Moratoriums, permits, power, water and capital behind the facilities that run these models.
Method
How the Model Hub is built
Sources, evidence labels, refresh behaviour, and the limits of every comparison here.