# Models, Page 493 of 501 Source: https://savrn.com/models/page/493 Markdown alternate of the page above; the site index is https://savrn.com/llms.txt --- 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. 12,010Models 3,413Datasets 288Papers 7,298Publishers 12,421Sourced relationships Updated 2026-10-21 · [How the library is built](https://savrn.com/model-hub/methodology) ## Filter Models Task - [Text generation1,467](https://savrn.com/models?task=Text+generation) - [Image and text to text542](https://savrn.com/models?task=Image+and+text+to+text) - [Robotics370](https://savrn.com/models?task=Robotics) - [Feature extraction352](https://savrn.com/models?task=Feature+extraction) - [Text classification326](https://savrn.com/models?task=Text+classification) - [Text to image224](https://savrn.com/models?task=Text+to+image) - [Speech recognition176](https://savrn.com/models?task=Speech+recognition) - [Audio classification160](https://savrn.com/models?task=Audio+classification) - [Text to speech141](https://savrn.com/models?task=Text+to+speech) - [Image classification138](https://savrn.com/models?task=Image+classification) - [Sentence similarity103](https://savrn.com/models?task=Sentence+similarity) - [Token classification97](https://savrn.com/models?task=Token+classification) - [Reinforcement learning96](https://savrn.com/models?task=Reinforcement+learning) - [Zero-shot classification93](https://savrn.com/models?task=Zero-shot+classification) - [Image segmentation90](https://savrn.com/models?task=Image+segmentation) - [Object detection86](https://savrn.com/models?task=Object+detection) - [Any to any79](https://savrn.com/models?task=Any+to+any) - [Translation79](https://savrn.com/models?task=Translation) - [Question answering73](https://savrn.com/models?task=Question+answering) - [Fill mask69](https://savrn.com/models?task=Fill+mask) - [Time series forecasting64](https://savrn.com/models?task=Time+series+forecasting) - [Video classification60](https://savrn.com/models?task=Video+classification) - [Image to text59](https://savrn.com/models?task=Image+to+text) - [Text to video55](https://savrn.com/models?task=Text+to+video) Library - [transformers2,877](https://savrn.com/models?library=transformers) - [peft357](https://savrn.com/models?library=peft) - [diffusers199](https://savrn.com/models?library=diffusers) - [pytorch189](https://savrn.com/models?library=pytorch) - [gguf175](https://savrn.com/models?library=gguf) - [lerobot148](https://savrn.com/models?library=lerobot) - [mlx148](https://savrn.com/models?library=mlx) - [sentence-transformers139](https://savrn.com/models?library=sentence-transformers) - [timm49](https://savrn.com/models?library=timm) - [transformers.js45](https://savrn.com/models?library=transformers.js) - [flaxspeaker44](https://savrn.com/models?library=flaxspeaker) - [llama.cpp44](https://savrn.com/models?library=llama.cpp) - [onnx39](https://savrn.com/models?library=onnx) - [vllm38](https://savrn.com/models?library=vllm) - [openpi35](https://savrn.com/models?library=openpi) - [diffusion-single-file28](https://savrn.com/models?library=diffusion-single-file) - [minimax-h326](https://savrn.com/models?library=minimax-h3) - [ultralytics24](https://savrn.com/models?library=ultralytics) - [PaddleOCR22](https://savrn.com/models?library=PaddleOCR) - [openvino20](https://savrn.com/models?library=openvino) - [exllamav319](https://savrn.com/models?library=exllamav3) - [coreml18](https://savrn.com/models?library=coreml) - [litert17](https://savrn.com/models?library=litert) - [rkllm15](https://savrn.com/models?library=rkllm) Modality - [Other6,847](https://savrn.com/models?modality=Other) - [Text2,701](https://savrn.com/models?modality=Text) - [Image and text601](https://savrn.com/models?modality=Image+and+text) - [Image586](https://savrn.com/models?modality=Image) - [Audio495](https://savrn.com/models?modality=Audio) - [Control466](https://savrn.com/models?modality=Control) - [Video115](https://savrn.com/models?modality=Video) - [Multimodal79](https://savrn.com/models?modality=Multimodal) - [Time series64](https://savrn.com/models?modality=Time+series) - [Tabular56](https://savrn.com/models?modality=Tabular) License - [apache-2.03,220](https://savrn.com/models?license=apache-2.0) - [mit1,282](https://savrn.com/models?license=mit) - [other743](https://savrn.com/models?license=other) - [cc-by-nc-4.0201](https://savrn.com/models?license=cc-by-nc-4.0) - [cc-by-4.0155](https://savrn.com/models?license=cc-by-4.0) - [bsd-3-clause108](https://savrn.com/models?license=bsd-3-clause) - [gemma63](https://savrn.com/models?license=gemma) - [cc-by-nc-sa-4.051](https://savrn.com/models?license=cc-by-nc-sa-4.0) - [llama3.240](https://savrn.com/models?license=llama3.2) - [agpl-3.032](https://savrn.com/models?license=agpl-3.0) - [unknown29](https://savrn.com/models?license=unknown) - [llama3.128](https://savrn.com/models?license=llama3.1) - [cc-by-sa-4.020](https://savrn.com/models?license=cc-by-sa-4.0) - [gpl-3.017](https://savrn.com/models?license=gpl-3.0) - [openrail++17](https://savrn.com/models?license=openrail%2B%2B) - [openmdw-1.115](https://savrn.com/models?license=openmdw-1.1) - [llama314](https://savrn.com/models?license=llama3) - [openrail14](https://savrn.com/models?license=openrail) - [cc-by-nc-nd-4.013](https://savrn.com/models?license=cc-by-nc-nd-4.0) - [creativeml-openrail-m13](https://savrn.com/models?license=creativeml-openrail-m) - [llama28](https://savrn.com/models?license=llama2) - [afl-3.07](https://savrn.com/models?license=afl-3.0) - [osl-3.06](https://savrn.com/models?license=osl-3.0) - [cc0-1.04](https://savrn.com/models?license=cc0-1.0) Access - [Open weights11,627](https://savrn.com/models?access=open_access) - [Access requested at publisher383](https://savrn.com/models?access=gated) Publisher - [Team Mradermacher313](https://savrn.com/models?publisher=mradermacher) - [Yurun Yuan106](https://savrn.com/models?publisher=ryanyr) - [RunningHub.ai101](https://savrn.com/models?publisher=runninghubai) - [Qwen91](https://savrn.com/models?publisher=qwen) - [Jenny Wilson85](https://savrn.com/models?publisher=jenny08311) - [Jessen Pu77](https://savrn.com/models?publisher=putty77) - [RKNNAI73](https://savrn.com/models?publisher=rknnai) - [AI at Meta72](https://savrn.com/models?publisher=facebook) - [Convergent Intelligence66](https://savrn.com/models?publisher=reaperdoesntknow) - [Google64](https://savrn.com/models?publisher=google) - [Yurun Yuan63](https://savrn.com/models?publisher=yurunyyr) - [Firza Hadzami61](https://savrn.com/models?publisher=firzahdzm) - [Zeyuan Yang59](https://savrn.com/models?publisher=miiche) - [Yurun Yuan59](https://savrn.com/models?publisher=yuruny) - [Yanggangu57](https://savrn.com/models?publisher=yanggangu) - [Hongao56](https://savrn.com/models?publisher=cisco1963) - [Francesca Padovani53](https://savrn.com/models?publisher=francesca9805) - [Szekely52](https://savrn.com/models?publisher=attila115) - [Yurun Yuan51](https://savrn.com/models?publisher=yyuan244) - [Wang49](https://savrn.com/models?publisher=davidwdw) - [Christopher Subia-Waud48](https://savrn.com/models?publisher=cwaud) - [Microsoft48](https://savrn.com/models?publisher=microsoft) - [NVIDIA48](https://savrn.com/models?publisher=nvidia) - [BAAR46](https://savrn.com/models?publisher=aixk) [Most downloaded](https://savrn.com/models?sort=downloads)[Most liked](https://savrn.com/models?sort=likes)[Recently updated](https://savrn.com/models?sort=updated)[Name](https://savrn.com/models?sort=name)[Largest](https://savrn.com/models?sort=params) 12,010 models, sorted by most downloaded. Model ### [visualrl-qwen3vl4b-ppo1-visionsr1-r19-r2-fix](https://savrn.com/models/visualrl-qwen3vl4b-ppo1-visionsr1-r19-r2-fix) [Zeyuan Yang](https://savrn.com/model-publishers/miiche) Open weights [View model](https://savrn.com/models/visualrl-qwen3vl4b-ppo1-visionsr1-r19-r2-fix) Model ### [visualrl-qwen3vl4b-ppo1-visionsr1-r2-clean](https://savrn.com/models/visualrl-qwen3vl4b-ppo1-visionsr1-r2-clean) [Zeyuan Yang](https://savrn.com/model-publishers/miiche) Open weights [View model](https://savrn.com/models/visualrl-qwen3vl4b-ppo1-visionsr1-r2-clean) Model ### [visualrl-qwen3vl4b-ppo1-visionsr1-r91-hires-fix](https://savrn.com/models/visualrl-qwen3vl4b-ppo1-visionsr1-r91-hires-fix) [Zeyuan Yang](https://savrn.com/model-publishers/miiche) Open weights [View model](https://savrn.com/models/visualrl-qwen3vl4b-ppo1-visionsr1-r91-hires-fix) Model ### [visualrl-qwen3vl4b-vppo-4bx-c10-fix](https://savrn.com/models/visualrl-qwen3vl4b-vppo-4bx-c10-fix) [Zeyuan Yang](https://savrn.com/model-publishers/miiche) Open weights [View model](https://savrn.com/models/visualrl-qwen3vl4b-vppo-4bx-c10-fix) Model ### [visualrl-qwen3vl4b-vppo-k01-fix](https://savrn.com/models/visualrl-qwen3vl4b-vppo-k01-fix) [Zeyuan Yang](https://savrn.com/model-publishers/miiche) Open weights [View model](https://savrn.com/models/visualrl-qwen3vl4b-vppo-k01-fix) Model ### [visualrl-qwen3vl4b-vppo-k09-fix](https://savrn.com/models/visualrl-qwen3vl4b-vppo-k09-fix) [Zeyuan Yang](https://savrn.com/model-publishers/miiche) Open weights [View model](https://savrn.com/models/visualrl-qwen3vl4b-vppo-k09-fix) Model ### [visualrl-rscore](https://savrn.com/models/visualrl-rscore) [Zeyuan Yang](https://savrn.com/model-publishers/miiche) Open weights [View model](https://savrn.com/models/visualrl-rscore) Model ### [vit-checkpoint](https://savrn.com/models/vit-checkpoint) [Melissa Rivera](https://savrn.com/model-publishers/melissarivera) A research-oriented ViT prototype targeting Contrastive. The included giant setup documents defaults and file formats without presenting unverified performance numbers. - The Python file contains the model and runnable example or training entry point. - config.json records the generated architecture settings. - trainingargs.json records the default experiment recipe. - model.safetensors is a valid initialization checkpoint for smoke tests; it is not presented as a trained benchmark checkpoint. - No benchmark score is claimed in this repository. The included configuration uses sgd with a linear warmup schedule. These are starting values in the script, not evidence of a completed run. For a… Open weights mit 16,576 parameters 256 tokens [View model](https://savrn.com/models/vit-checkpoint) Model ### [vit-checkpoint](https://savrn.com/models/vit-checkpoint-2) [Ibrahim Simsek](https://savrn.com/model-publishers/ibrahimsimsek) A research-oriented ViT prototype targeting Multitask. The included large setup documents defaults and file formats without presenting unverified performance numbers. - The Python file contains the model and runnable example or training entry point. - config.json records the generated architecture settings. - trainingargs.json records the default experiment recipe. - model.safetensors is a valid initialization checkpoint for smoke tests; it is not presented as a trained benchmark checkpoint. - No benchmark score is claimed in this repository. The included configuration uses sgd with a linear warmup schedule. These are starting values in the script, not evidence of a completed run. For a… Open weights mit 33,088 parameters 256 tokens [View model](https://savrn.com/models/vit-checkpoint-2) Model ### [vit-matching-slim](https://savrn.com/models/vit-matching-slim) [Alvaro Martin](https://savrn.com/model-publishers/alvaromar) Working implementation of ViT for Matching using a giant configuration. The repository focuses on transparent code and repeatable smoke tests; benchmark claims are deliberately omitted. - The Python file contains the model and runnable example or training entry point. - config.json records the generated architecture settings. - trainingargs.json records the default experiment recipe. - model.safetensors is a valid initialization checkpoint for smoke tests; it is not presented as a trained benchmark checkpoint. - No benchmark score is claimed in this repository. The included configuration uses adamw with a step schedule. These are starting values in the script, not evidence of a completed… Open weights mit 24,832 parameters 128 tokens [View model](https://savrn.com/models/vit-matching-slim) Model ### [vit-multitask-run1](https://savrn.com/models/vit-multitask-run1) [Viveknairly](https://savrn.com/model-publishers/viveknairly) This repository is a compact, custom PyTorch implementation of ViT for Multitask. The small configuration is intended for code review, smoke tests, and small controlled experiments rather than as a production-ready pretrained release. - The Python file contains the model and runnable example or training entry point. - config.json records the generated architecture settings. - trainingargs.json records the default experiment recipe. - model.safetensors is a valid initialization checkpoint for smoke tests; it is not presented as a trained benchmark checkpoint. - No benchmark score is claimed in this repository. The included configuration uses lamb with a step schedule. These are starting… Open weights mit 16,576 parameters 512 tokens [View model](https://savrn.com/models/vit-multitask-run1) Model ### [vit-retrieval](https://savrn.com/models/vit-retrieval) [Ruby Williams](https://savrn.com/model-publishers/jfjames38) This is an experimental ViT codebase for Retrieval. It keeps the nano setup intentionally manageable so architecture changes can be inspected before a full training run. - The Python file contains the model and runnable example or training entry point. - config.json records the generated architecture settings. - trainingargs.json records the default experiment recipe. - model.safetensors is a valid initialization checkpoint for smoke tests; it is not presented as a trained benchmark checkpoint. - No benchmark score is claimed in this repository. The included configuration uses lamb with a polynomial schedule. These are starting values in the script, not evidence of a completed run. For a… Open weights bsd-3-clause 49,600 parameters 256 tokens [View model](https://savrn.com/models/vit-retrieval) Model ### [vit-retrieval-alpha70](https://savrn.com/models/vit-retrieval-alpha70) [Christian Krause](https://savrn.com/model-publishers/christiankrause) A small ViT implementation for Retrieval, packaged with an explicit configuration and an initialization checkpoint. The giant variant is a reproducible starting point, not a trained model release. - The Python file contains the model and runnable example or training entry point. - config.json records the generated architecture settings. - trainingargs.json records the default experiment recipe. - model.safetensors is a valid initialization checkpoint for smoke tests; it is not presented as a trained benchmark checkpoint. - No benchmark score is claimed in this repository. The included configuration uses sgd with a onecycle schedule. These are starting values in the script, not evidence of a… Open weights bsd-3-clause 49,600 parameters 256 tokens [View model](https://savrn.com/models/vit-retrieval-alpha70) Model ### [vitoom-nunchaku](https://savrn.com/models/vitoom-nunchaku) [Zhang](https://savrn.com/model-publishers/tonera) English | 中文 Community-maintained fork of Nunchaku. Nunchaku is an SVDQuant inference engine for 4-bit diffusion models (paper: SVDQuant). The upstream project has not been actively maintained for a long time. This fork keeps the original capabilities while extending model and quantization support, and distributes prebuilt wheels on Hugging Face. Quantized inference for three additional models. Published wheels cover Linux x8664, Linux aarch64, and Windows, all built for CUDA 13.0: - Linux x8664: Python 3.11 + PyTorch 2.11; Python 3.11 / 3.12 / 3.13 + PyTorch 2.14 File names are listed under Prebuilt Wheels. Anima checkpoints store plain INT8. frompretrained(..., device="cuda") packs them… Open weights apache-2.0 nunchaku [View model](https://savrn.com/models/vitoom-nunchaku) Model ### [vixenmami](https://savrn.com/models/vixenmami) [Omar](https://savrn.com/model-publishers/omarpiose) Open weights [View model](https://savrn.com/models/vixenmami) Model · Zero-shot classification ### [viya-base](https://savrn.com/models/viya-base) [Ho Hiep](https://savrn.com/model-publishers/hiepho) VIYA reads Vietnamese text and returns typed decisions with calibrated confidence in a single forward pass. It does not generate text: you describe the question and the options in plain language, and VIYA scores every option. Options are free text, so you can add or rename them without retraining. - Vietnamese fact-checking. 87.6 macro-F1 on ViFactCheck with gold evidence (human: 84.9). When it has to find the evidence itself in the full article, it scores 78.7, ahead of Gemini 1.5 Flash, XLM-R large and Mistral 7B. - Full fact-checking pipeline. On ViWikiFC, VIYA finds the right evidence sentence and reaches the right verdict 75.7% of the time; the best published pipeline reaches 67.0%.… Open weights apache-2.0 322M parameters [View model](https://savrn.com/models/viya-base) Model · Robotics ### [vla-hand-baselines](https://savrn.com/models/vla-hand-baselines) [MIT-media-lab-tactile-vla-hand](https://savrn.com/model-publishers/mit-media-lab) Checkpoints of the two external baselines trained against V4 in the VLA-HAND project. Both were trained and tested on the same three domains (GigaHands, OakInk2, TACO), splits, normalisation statistics and test protocol as V4. Each is the checkpoint with the lowest validation loss, the one all reported test numbers come from. Test split, the first 8 control steps of each test window, three domains pooled. Wrist translation in cm, wrist rotation in degrees (geodesic), fingers in cm; lower is better. VITRA predicts joint angles, so its finger error is measured after MANO forward kinematics and includes an FK floor that SmolVLA does not have. The finger columns are not directly comparable.… Open weights other [View model](https://savrn.com/models/vla-hand-baselines) Model · Robotics ### [vla-hand-table1](https://savrn.com/models/vla-hand-table1) [MIT-media-lab-tactile-vla-hand](https://savrn.com/model-publishers/mit-media-lab) Adapted checkpoints for the EgoTouch Table 1 protocol. The model folder follows the layout used by MIT-Media-Lab/vla-hand-baselines. Open weights other [View model](https://savrn.com/models/vla-hand-table1) Model ### [vla-recipe-ckpts](https://savrn.com/models/vla-recipe-ckpts) [Jongyeol, Na](https://savrn.com/model-publishers/najongs) Open weights [View model](https://savrn.com/models/vla-recipe-ckpts) Model ### [vlatest](https://savrn.com/models/vlatest) [RocheL](https://savrn.com/model-publishers/rochel) Access requested at publisher [View model](https://savrn.com/models/vlatest) Model · Visual question answering ### [vlm-calibration-prefix-vqav2](https://savrn.com/models/vlm-calibration-prefix-vqav2) [Bhaskar C](https://savrn.com/model-publishers/25b3nk) A small non-autoregressive yes/no visual question answering model built for research on calibrated decisions. It answers a yes/no question about an image in one forward pass, with no generation and no verbalised confidence. The confidence is the softmax over two token logits followed by a single post-hoc temperature. - Image. A frozen SigLIP2-base encodes the image into its pooled vector (pooleroutput, 768-d). - Prefix token. That vector becomes one prefix token, prepended to the input embeddings of ModernBERT-base: - anchor is a learned token, initialised from the " image" embedding. - alpha is a scalar gate, initialised to 0, so the model starts as exactly the text-only model. - gmax caps… Open weights apache-2.0 150M parameters pytorch [View model](https://savrn.com/models/vlm-calibration-prefix-vqav2) Model ### [vlm4vla_2B](https://savrn.com/models/vlm4vla-2b) [Kyujin Lee](https://savrn.com/model-publishers/kyujinl) Open weights [View model](https://savrn.com/models/vlm4vla-2b) Model ### [vlx-seek-onnx](https://savrn.com/models/vlx-seek-onnx) [Itcast666](https://savrn.com/model-publishers/itcast666) Open weights [View model](https://savrn.com/models/vlx-seek-onnx) Model · Text generation ### [vnpen-writer-2b-v0.1-preview](https://savrn.com/models/vnpen-writer-2b-v0-1-preview) [VNPen LLM Project](https://savrn.com/model-publishers/vnpen) VNPen is MewBaka Studio's visual-novel model series. The writer edition is for script writing, de-AI rewriting, and generating example scenes from a mood brief. Output format is one script line per line: speaker：text, with narration written as 旁白：. The base Qwen/Qwen3.5-2B is multimodal. Its checkpoint carries 297 model.visual. tensors (a depth-24 / hidden-1024 / patch-16 ViT) and 15 mtp. tensors for multi-token prediction. This project is text-only. In transformers, AutoModelForCausalLM on a qwen35 config builds Qwen35ForCausalLM over a Qwen35TextConfig — so the vision weights were never loaded at any point: not for training, not for merging, not for saving. Verified on the published… Open weights apache-2.0 1.9B parameters 262,144 tokens transformers [View model](https://savrn.com/models/vnpen-writer-2b-v0-1-preview) ## Model Collections Hand-picked starting points, each with the reason it exists. Collection · 4 entries ### [Embedding models for retrieval](https://savrn.com/collections/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. [View collection](https://savrn.com/collections/embedding-models-for-retrieval) Collection · 4 entries ### [Models that fit on one accelerator](https://savrn.com/collections/models-that-run-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. [View collection](https://savrn.com/collections/models-that-run-on-one-accelerator) Collection · 6 entries ### [Open-weight text models worth knowing](https://savrn.com/collections/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. [View collection](https://savrn.com/collections/open-weight-text-models-worth-knowing) Collection · 3 entries ### [Speech and audio models](https://savrn.com/collections/speech-and-audio) Recognition and synthesis models, grouped so the two directions are easy to compare. [View collection](https://savrn.com/collections/speech-and-audio) ## 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](https://savrn.com/ai-index/pricing/open-models) The same open-weight model priced by every host that serves it, per million tokens. Research Hub ### [Data center trackers and maps](https://savrn.com/data-center-research) Moratoriums, permits, power, water and capital behind the facilities that run these models. Method ### [How the Model Hub is built](https://savrn.com/model-hub/methodology) Sources, evidence labels, refresh behaviour, and the limits of every comparison here.