# Models, Page 285 of 501 Source: https://savrn.com/models/page/285 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 · Image and text to text ### [clef-flash-4bit](https://savrn.com/models/clef-flash-4bit) [MLX Community](https://savrn.com/model-publishers/mlx-community) Cloudflare/clef-flash converted to MLX (4-bit) for Apple Silicon. Clef turns a state (text, JSON, images, or video) plus a schema of typed questions into a probability for every allowed option, in a single forward pass. It is not a chat model — mlxvlm.generate, mlxlm.generate, and LM Studio will load the backbone but produce meaningless text. Use the bundled clefmlx.py loader, which runs the backbone and the joint schema head. Images (PIL) and videos (frame arrays) go in images / videos, as in the original: See the original model card for the input format, question types, and benchmarks. - processorconfig.json is the original from Cloudflare/clef-flash; prompt/token layout matches the… Open weights apache-2.0 9.4B parameters 262,144 tokens mlx [View model](https://savrn.com/models/clef-flash-4bit) Model · Image and text to text ### [clef-flash-8bit](https://savrn.com/models/clef-flash-8bit) [MLX Community](https://savrn.com/model-publishers/mlx-community) Cloudflare/clef-flash converted to MLX (8-bit) for Apple Silicon. Clef turns a state (text, JSON, images, or video) plus a schema of typed questions into a probability for every allowed option, in a single forward pass. It is not a chat model — mlxvlm.generate, mlxlm.generate, and LM Studio will load the backbone but produce meaningless text. Use the bundled clefmlx.py loader, which runs the backbone and the joint schema head. Images (PIL) and videos (frame arrays) go in images / videos, as in the original: See the original model card for the input format, question types, and benchmarks. - processorconfig.json is the original from Cloudflare/clef-flash; prompt/token layout matches the… Open weights apache-2.0 9.4B parameters 262,144 tokens mlx [View model](https://savrn.com/models/clef-flash-8bit) Model · Text classification ### [clefsift](https://savrn.com/models/clefsift) [Stephen Murray](https://savrn.com/model-publishers/spmurrayzzz) ClefSift is an experimental English text classifier fine-tuned from Cloudflare/Clef. It returns scores for four document-level labels in one forward pass: These are provisional, process-based labels. The model sees writing style, not the author's actual workflow. Its output does not prove authorship. Do not use it as the sole basis for academic, employment, or moderation decisions. This release uses the selected v2 step-128 checkpoint. The additional rank-64 LoRA weights are merged into the BF16 backbone. The trained joint decision head is stored separately in FP32. This is a decision model, not a chat model. The retained config and loader use the Qwen3.5 architecture identifiers above. Pin… Open weights apache-2.0 27.4B parameters 262,144 tokens transformers [View model](https://savrn.com/models/clefsift) Model ### [client-assets](https://savrn.com/models/client-assets) [Gongting](https://savrn.com/model-publishers/gongting) Versioned model and runtime packages for the desktop client. Each package is verified by SHA-256 Open weights [View model](https://savrn.com/models/client-assets) Model · Token classification ### [clinical-evidence-gliner2.5-base-lora-v3-act-sol](https://savrn.com/models/clinical-evidence-gliner2-5-base-lora-v3-act-sol) [Natthawut Adulyanukosol](https://savrn.com/model-publishers/na399) The model identifies candidate clinical evidence spans in English text. Its v3 schema has six core entity types and explicit attributes. Shared attributes are three complete, qualified, single-label groups: assertion (affirmed, hypothetical, negated, ruled out, uncertain), experiencer (patient, family, other), and time frame (current, recent, historical, future). The registry also defines family-specific choice and literal-span labels. Use the complete versioned schema in schemav3.json; do not substitute an open-ended or partial attribute schema. An absent axis in a source row was masked during training; it was not a negative or an implicit default. Defaults are ordinary explicit values… Open weights apache-2.0 peft [View model](https://savrn.com/models/clinical-evidence-gliner2-5-base-lora-v3-act-sol) Model · Token classification ### [clinical-evidence-gliner2.5-lora-v3-act-sol-17089](https://savrn.com/models/clinical-evidence-gliner2-5-lora-v3-act-sol-17089) [Natthawut Adulyanukosol](https://savrn.com/model-publishers/na399) This is the epoch 4 LoRA adapter from job 17089, trained to extract exact clinical evidence spans and explicit attributes under the ClinicalEvidence v3 span schema. It is an individual research adapter, not the final winner of the current multi-seed campaign. The repository contains a PEFT adapter. Load it on the pinned public base model, then pass the v3 schema. The base revision below is a verified public reference snapshot whose core runtime assets match the frozen base assets used in this campaign; it does not establish the historical resolved revision used by the training process. The code above is illustrative and was not executed as part of this card. Use schemav3.json for the… Open weights other peft [View model](https://savrn.com/models/clinical-evidence-gliner2-5-lora-v3-act-sol-17089) Model · Token classification ### [clinical-evidence-gliner2.5-small-lora-v3-act-sol](https://savrn.com/models/clinical-evidence-gliner2-5-small-lora-v3-act-sol) [Natthawut Adulyanukosol](https://savrn.com/model-publishers/na399) The model identifies candidate clinical evidence spans in English text. Its v3 schema has six core entity types and explicit attributes. Shared attributes are three complete, qualified, single-label groups: assertion (affirmed, hypothetical, negated, ruled out, uncertain), experiencer (patient, family, other), and time frame (current, recent, historical, future). The registry also defines family-specific choice and literal-span labels. Use the complete versioned schema in schemav3.json; do not substitute an open-ended or partial attribute schema. An absent axis in a source row was masked during training; it was not a negative or an implicit default. Defaults are ordinary explicit values… Open weights apache-2.0 peft [View model](https://savrn.com/models/clinical-evidence-gliner2-5-small-lora-v3-act-sol) Model ### [clip-checkpoint](https://savrn.com/models/clip-checkpoint) [Felix Sari](https://savrn.com/model-publishers/felixsari) Working implementation of CLIP for Multitask 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 33,088 parameters 512 tokens [View model](https://savrn.com/models/clip-checkpoint) Model ### [clip-classification-warmup](https://savrn.com/models/clip-classification-warmup) [Jason H. Lopez](https://savrn.com/model-publishers/llopezjason) A small CLIP implementation for Classification, packaged with an explicit configuration and an initialization checkpoint. The large 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 adamw with a exponential schedule. These are starting values in the script, not… Open weights bsd-3-clause 49,600 parameters 256 tokens [View model](https://savrn.com/models/clip-classification-warmup) Model ### [clip-contrastive](https://savrn.com/models/clip-contrastive) [Jacob Davis](https://savrn.com/model-publishers/jacobdaviswos) This repository is a compact, custom PyTorch implementation of CLIP for Contrastive. The nano 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 adamw with a step schedule. These are starting… Open weights apache-2.0 16,576 parameters 512 tokens [View model](https://savrn.com/models/clip-contrastive) Model ### [clip-contrastive-lab27](https://savrn.com/models/clip-contrastive-lab27) [Abdulrahman Alshehri](https://savrn.com/model-publishers/aalshehri52) A small CLIP implementation for Contrastive, packaged with an explicit configuration and an initialization checkpoint. The xlarge 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 linear warmup schedule. These are starting values in the script, not… Open weights bsd-3-clause 24,832 parameters 256 tokens [View model](https://savrn.com/models/clip-contrastive-lab27) Model ### [clip-matching](https://savrn.com/models/clip-matching) [Marcus HO](https://savrn.com/model-publishers/marcusho0509) A small CLIP implementation for Matching, packaged with an explicit configuration and an initialization checkpoint. The xlarge 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 novograd with a polynomial schedule. These are starting values in the script, not… Open weights bsd-3-clause 16,576 parameters 128 tokens [View model](https://savrn.com/models/clip-matching) Model ### [clip-matching](https://savrn.com/models/clip-matching-2) [Freja Andersson](https://savrn.com/model-publishers/tonyliu5) This is an experimental CLIP codebase for Matching. It keeps the large 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 adamw with a constant warmup schedule. These are starting values in the script, not evidence of a completed run.… Open weights mit 33,088 parameters 512 tokens [View model](https://savrn.com/models/clip-matching-2) Model ### [clip-matching](https://savrn.com/models/clip-matching-3) [Julia Schmidt](https://savrn.com/model-publishers/juliaschmidt0425) Working implementation of CLIP for Matching using a huge 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 novograd with a cosine schedule. These are starting values in the script, not evidence of a… Open weights apache-2.0 49,600 parameters 256 tokens [View model](https://savrn.com/models/clip-matching-3) Model ### [clip-matching](https://savrn.com/models/clip-matching-4) [Mykaur02](https://savrn.com/model-publishers/mykaur02) Open weights bsd-3-clause 24,832 parameters [View model](https://savrn.com/models/clip-matching-4) Model ### [clip-multitask](https://savrn.com/models/clip-multitask) [Daniil Kozlov](https://savrn.com/model-publishers/kkozlovdaniil) This is an experimental CLIP codebase for Multitask. It keeps the tiny 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 adam with a onecycle schedule. These are starting values in the script, not evidence of a completed run. For a… Open weights bsd-3-clause 49,600 parameters 128 tokens [View model](https://savrn.com/models/clip-multitask) Model ### [clip-multitask-base17-2024](https://savrn.com/models/clip-multitask-base17-2024) [Vitor PEREIRA](https://savrn.com/model-publishers/poapereira) This repository is a compact, custom PyTorch implementation of CLIP for Multitask. The giant 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 sgd with a constant warmup schedule. These are… Open weights mit 49,600 parameters 512 tokens [View model](https://savrn.com/models/clip-multitask-base17-2024) Model ### [clip-retrieval21-2024](https://savrn.com/models/clip-retrieval21-2024) [Olivia K. Taylor](https://savrn.com/model-publishers/sakuramor6) This repository is a compact, custom PyTorch implementation of CLIP for Retrieval. The large 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 novograd with a constant warmup schedule. These… Open weights bsd-3-clause 33,088 parameters 512 tokens [View model](https://savrn.com/models/clip-retrieval21-2024) Model · Zero shot image classification ### [clip-vit-base-patch16](https://savrn.com/models/clip-vit-base-patch16-2) [Dang Quoc Dung](https://savrn.com/model-publishers/dungdq1) https://huggingface.co/openai/clip-vit-base-patch16 with ONNX weights to be compatible with Transformers.js. If you haven't already, you can install the Transformers.js JavaScript library from NPM using: Example: Perform zero-shot image classification with the pipeline API. Example: Compute vision embeddings with CLIPVisionModelWithProjection. Note: Having a separate repo for ONNX weights is intended to be a temporary solution until WebML gains more traction. If you would like to make your models web-ready, we recommend converting to ONNX using Optimum and structuring your repo like this one (with ONNX weights located in a subfolder named onnx). Open weights 77 tokens transformers.js [View model](https://savrn.com/models/clip-vit-base-patch16-2) Model ### [clips-studio-releases](https://savrn.com/models/clips-studio-releases) [Colin](https://savrn.com/model-publishers/colingpt9) This repository is not a model. It holds the installer payload for Clips Kitty, a free, open-source AI video clipping app that runs entirely on your own Windows PC. It lives on Hugging Face for one dull reason: a GitHub release asset is capped at 2 GiB and the payload is roughly twice that, because the installer bundles everything the app needs rather than sending you off to install it yourself. They will not do anything on their own. Get the installer instead: One click, updates itself, and no Windows security prompt — Microsoft signed it. The Web Setup is about 1 MB. Run it, and it fetches the payload from here by itself, checks it against the SHA512 in latest.yml, and installs the app.… Open weights agpl-3.0 [View model](https://savrn.com/models/clips-studio-releases) Model · Text classification ### [clm](https://savrn.com/models/clm) [Ollaya](https://savrn.com/model-publishers/ollaya-dev) Ollaya package of Contrastive-LM/CLM-v0.1-8B and Qwen/Qwen3-8B by Contrastive-LM (projection heads) and the Qwen team (Qwen3-8B encoder). Ollaya runs open decision models locally, the way Ollama runs LLMs: typed questions in, calibrated answers out, behind a TypeSafe-compatible API. This repository holds only the files Ollaya derives, with no weights. Each graph is an ONNX export of the original model whose weights reference the authors' own weight files by byte offset, so ollaya pull downloads the weights from the upstream repositories, unmodified and pinned to a commit, and verifies their sha256. Each tag has an fp32 graph, used on CPU and GPU. Each tag also has decision.json (sequence… Open weights apache-2.0 onnx [View model](https://savrn.com/models/clm) Model · Robotics ### [cloud_so_bottle_0.6_torque](https://savrn.com/models/cloud-so-bottle-0-6-torque) [Kim Min Jung](https://savrn.com/model-publishers/wego-mink) Action Chunking with Transformers (ACT) is an imitation-learning method that predicts short action chunks instead of single steps. It learns from teleoperated data and often achieves high success rates. This policy has been trained and pushed to the Hub using LeRobot. See the full documentation at LeRobot Docs. For a complete walkthrough, see the training guide. Below is the short version on how to train and run inference/eval: Writes checkpoints to outputs/train/ /checkpoints/. Prefix the dataset repo with eval\ and supply --policy.path pointing to a local or hub checkpoint. Open weights apache-2.0 52M parameters lerobot [View model](https://savrn.com/models/cloud-so-bottle-0-6-torque) Model · Image and text to text ### [clover-1-150b-preview](https://savrn.com/models/clover-1-150b-preview) [Kitani](https://savrn.com/model-publishers/kitaniai) libraryname: transformers pipelinetag: image-text-to-text basemodel: - Qwen/Qwen3.8-27B - clover - mixture-of-experts - multimodal - reasoning - open-weights - custom-code Clover 1 150B Preview is the first public checkpoint of Clover 1, an experimental MoE model we're developing at Kitani. It's based on Qwen3.8-27B, but it isn't just a finetune with a different name. We kept much of Qwen3.8's underlying architecture, including the tokenizer, multimodal components, hybrid language backbone, embeddings, and LM head, while replacing the language model's dense FFNs with our own sparse mixture-of-experts setup. Clover currently has 8 full-sized experts per language layer with top-1 routing. The… Open weights apache-2.0 147.6B parameters 262,144 tokens transformers [View model](https://savrn.com/models/clover-1-150b-preview) Model ### [clrbr30](https://savrn.com/models/clrbr30) [Billy buckets](https://savrn.com/model-publishers/billybuckets) Open weights [View model](https://savrn.com/models/clrbr30) ## 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.