# Models, Page 314 of 489 Source: https://savrn.com/models/page/314 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. 11,734Models 3,323Datasets 288Papers 7,150Publishers 12,282Sourced relationships Updated 2026-10-20 · [How the library is built](https://savrn.com/model-hub/methodology) ## Filter Models Task - [Text generation1,441](https://savrn.com/models?task=Text+generation) - [Image and text to text530](https://savrn.com/models?task=Image+and+text+to+text) - [Feature extraction351](https://savrn.com/models?task=Feature+extraction) - [Robotics345](https://savrn.com/models?task=Robotics) - [Text classification310](https://savrn.com/models?task=Text+classification) - [Text to image222](https://savrn.com/models?task=Text+to+image) - [Speech recognition175](https://savrn.com/models?task=Speech+recognition) - [Audio classification158](https://savrn.com/models?task=Audio+classification) - [Image classification138](https://savrn.com/models?task=Image+classification) - [Text to speech137](https://savrn.com/models?task=Text+to+speech) - [Sentence similarity103](https://savrn.com/models?task=Sentence+similarity) - [Token classification97](https://savrn.com/models?task=Token+classification) - [Reinforcement learning95](https://savrn.com/models?task=Reinforcement+learning) - [Zero-shot classification93](https://savrn.com/models?task=Zero-shot+classification) - [Image segmentation89](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) - [Image to text59](https://savrn.com/models?task=Image+to+text) - [Video classification59](https://savrn.com/models?task=Video+classification) - [Text to video55](https://savrn.com/models?task=Text+to+video) Library - [transformers2,829](https://savrn.com/models?library=transformers) - [peft355](https://savrn.com/models?library=peft) - [diffusers196](https://savrn.com/models?library=diffusers) - [pytorch184](https://savrn.com/models?library=pytorch) - [gguf172](https://savrn.com/models?library=gguf) - [mlx145](https://savrn.com/models?library=mlx) - [lerobot141](https://savrn.com/models?library=lerobot) - [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) - [diffusion-single-file28](https://savrn.com/models?library=diffusion-single-file) - [minimax-h324](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) - [exllamav318](https://savrn.com/models?library=exllamav3) - [coreml17](https://savrn.com/models?library=coreml) - [litert16](https://savrn.com/models?library=litert) - [openpi16](https://savrn.com/models?library=openpi) - [rkllm15](https://savrn.com/models?library=rkllm) Modality - [Other6,664](https://savrn.com/models?modality=Other) - [Text2,658](https://savrn.com/models?modality=Text) - [Image and text589](https://savrn.com/models?modality=Image+and+text) - [Image582](https://savrn.com/models?modality=Image) - [Audio488](https://savrn.com/models?modality=Audio) - [Control440](https://savrn.com/models?modality=Control) - [Video114](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-2.03,175](https://savrn.com/models?license=apache-2.0) - [mit1,275](https://savrn.com/models?license=mit) - [other723](https://savrn.com/models?license=other) - [cc-by-nc-4.0200](https://savrn.com/models?license=cc-by-nc-4.0) - [cc-by-4.0153](https://savrn.com/models?license=cc-by-4.0) - [bsd-3-clause107](https://savrn.com/models?license=bsd-3-clause) - [gemma63](https://savrn.com/models?license=gemma) - [cc-by-nc-sa-4.050](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 weights11,363](https://savrn.com/models?access=open_access) - [Access requested at publisher371](https://savrn.com/models?access=gated) Publisher - [Team Mradermacher304](https://savrn.com/models?publisher=mradermacher) - [Yurun Yuan101](https://savrn.com/models?publisher=ryanyr) - [RunningHub.ai100](https://savrn.com/models?publisher=runninghubai) - [Qwen91](https://savrn.com/models?publisher=qwen) - [Jenny Wilson81](https://savrn.com/models?publisher=jenny08311) - [RKNNAI73](https://savrn.com/models?publisher=rknnai) - [AI at Meta72](https://savrn.com/models?publisher=facebook) - [Jessen Pu71](https://savrn.com/models?publisher=putty77) - [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) - [Yanggangu57](https://savrn.com/models?publisher=yanggangu) - [Hongao56](https://savrn.com/models?publisher=cisco1963) - [Yurun Yuan55](https://savrn.com/models?publisher=yuruny) - [Francesca Padovani53](https://savrn.com/models?publisher=francesca9805) - [Wang49](https://savrn.com/models?publisher=davidwdw) - [Microsoft48](https://savrn.com/models?publisher=microsoft) - [BAAR46](https://savrn.com/models?publisher=aixk) - [NVIDIA46](https://savrn.com/models?publisher=nvidia) - [Khazzz1c44](https://savrn.com/models?publisher=khazic) - [Quan44](https://savrn.com/models?publisher=wq2012) - [Yurun Yuan44](https://savrn.com/models?publisher=yyuan244) [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) 11,734 models, sorted by most downloaded. Model · Text generation ### [deepseek-v4.1-flash](https://savrn.com/models/deepseek-v4-1-flash-2) [Tiny Random](https://savrn.com/model-publishers/tiny-random) Open weights 68M parameters transformers [View model](https://savrn.com/models/deepseek-v4-1-flash-2) Model · Text generation ### [deepseek-v4.1-flash-1017](https://savrn.com/models/deepseek-v4-1-flash-1017-2) [Tiny Random](https://savrn.com/model-publishers/tiny-random) Open weights 68M parameters transformers [View model](https://savrn.com/models/deepseek-v4-1-flash-1017-2) Model ### [deeptrace-models](https://savrn.com/models/deeptrace-models) [Swapnil Chakraborty](https://savrn.com/model-publishers/swapnil05092004) Open weights [View model](https://savrn.com/models/deeptrace-models) Model ### [defect-aware-MAE](https://savrn.com/models/defect-aware-mae) [Shrey Patel](https://savrn.com/model-publishers/godseye1311) A Vision Transformer encoder pretrained without labels on steel-surface images with a masked autoencoder adapted to texture defects. Frozen features are clustered into defect categories. No class labels, bounding boxes or detection objective are used in pretraining, and no contrastive loss. Encoder: 224×224 grayscale input, 16×16 patches (196 tokens), 6 pre-norm Transformer layers, 12 heads, 768-d. The decoder in the MAE checkpoint has 2 layers and a 36-d output head: Decoder(depth=2) with dec.pred = torch.nn.Linear(256, 36). NEU-DET (hot-rolled steel strip, 6 defect classes, 1,800 images). Pretraining used only the 1,440-image training split. The 360-image validation split was held out… Open weights pytorch [View model](https://savrn.com/models/defect-aware-mae) Model ### [deit-classification](https://savrn.com/models/deit-classification) [Fiona Reyes](https://savrn.com/model-publishers/fionareyes) A research-oriented DeiT prototype targeting Classification. 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… Open weights apache-2.0 49,600 parameters 512 tokens [View model](https://savrn.com/models/deit-classification) Model ### [deit-classification50](https://savrn.com/models/deit-classification50) [Lily Jones](https://savrn.com/model-publishers/joneslily) Open weights apache-2.0 16,576 parameters [View model](https://savrn.com/models/deit-classification50) Model ### [deit-contrastive](https://savrn.com/models/deit-contrastive) [Sophia Harris](https://savrn.com/model-publishers/vellorerobotics7768) This repository is a compact, custom PyTorch implementation of DeiT for Contrastive. 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 sgd with a exponential schedule. These are… Open weights bsd-3-clause 24,832 parameters 256 tokens [View model](https://savrn.com/models/deit-contrastive) Model ### [deit-multitask-practice](https://savrn.com/models/deit-multitask-practice) [Yui Nakamura](https://savrn.com/model-publishers/thomasroma87) A research-oriented DeiT prototype targeting Multitask. The included xlarge 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 novograd with a constant warmup schedule. These are starting values in the script, not evidence of a completed run.… Open weights mit 49,600 parameters 256 tokens [View model](https://savrn.com/models/deit-multitask-practice) Model ### [deit-retrieval](https://savrn.com/models/deit-retrieval) [Daprice06](https://savrn.com/model-publishers/daprice06) This repository is a compact, custom PyTorch implementation of DeiT for Retrieval. The xlarge 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 cosine schedule. These are starting… Open weights mit 24,832 parameters 256 tokens [View model](https://savrn.com/models/deit-retrieval) Model · Text generation ### [delta](https://savrn.com/models/delta) [Convergent Intelligence](https://savrn.com/model-publishers/reaperdoesntknow) This is the model card of a transformers model that has been pushed on the Hub. Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. Use the code below to get started with the model. Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019). Open weights 410M parameters transformers [View model](https://savrn.com/models/delta) Model ### [demo-0922](https://savrn.com/models/demo-0922) [Zeuah DU](https://savrn.com/model-publishers/zehaoam) Open weights [View model](https://savrn.com/models/demo-0922) Model ### [demo_image](https://savrn.com/models/demo-image) [Ng Duy Anh](https://savrn.com/model-publishers/sotatek-anhnguyen76) Open weights [View model](https://savrn.com/models/demo-image) Model · Robotics ### [demodoctor-act-clean-s2](https://savrn.com/models/demodoctor-act-clean-s2) [Akteruzzaman Raihan Sikder](https://savrn.com/model-publishers/raihan-js) 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. Learn how to train and run it in the LeRobot act guide, or browse the full documentation. The policy consumes these observation features and produces these action features. Inputs Outputs New to LeRobot? These guides cover the full workflow: - Install LeRobot — set up the lerobot package. - Hardware setup — assemble, wire, and calibrate your robot and cameras. - Record data & train a policy — the end-to-end imitation-learning… Open weights apache-2.0 52M parameters lerobot [View model](https://savrn.com/models/demodoctor-act-clean-s2) Model ### [denoising_autoencoder](https://savrn.com/models/denoising-autoencoder) [George Perdrizet](https://savrn.com/model-publishers/gperdrizet) A convolutional autoencoder trained to remove Gaussian noise from 256×256 RGB images. The model learns the manifold of clean images and projects noisy inputs back onto this learned space. This model removes Gaussian noise from corrupted images by learning to map noisy images back to their clean versions. During training, the autoencoder learns the distribution of clean images, enabling it to filter out noise while preserving image content. - σ=75 (on 0-255 scale) Gaussian noise - Approximately 0.294 on [0,1] normalized scale This model is designed for educational purposes to demonstrate how autoencoders can learn to denoise images by understanding the structure of clean data. - Exploring… Open weights mit keras [View model](https://savrn.com/models/denoising-autoencoder) Model ### [dense-1-8](https://savrn.com/models/dense-1-8) [Yusheng Su](https://savrn.com/model-publishers/yushengsu) Open weights apache-2.0 [View model](https://savrn.com/models/dense-1-8) Model ### [design-3d-002](https://savrn.com/models/design-3d-002) [Quachttohai](https://savrn.com/model-publishers/quachtohai) This repository contains the frozen baseline for the from-scratch Blender multi-object generation experiment. - 3,600 total scenes - 18 scene families - 2–6 objects - 2,400 train - 600 validation - 600 test - family-disjoint split - 50,020,480 parameters - dmodel: 640 - tied embeddings The model learned Blender/Python program grammar very well, but numeric attribute binding remains the primary failure mode. training/checkpoints/best.pt Design 3D-002-R2 will use a structured scene representation and a deterministic compiler to Blender Python, while preserving the same underlying dataset and family-disjoint evaluation protocol. Official Blender 3.0.1 is used. The Blender executable itself is… Open weights [View model](https://savrn.com/models/design-3d-002) Model ### [design-3d-002-r2c](https://savrn.com/models/design-3d-002-r2c) [Quachttohai](https://savrn.com/model-publishers/quachtohai) Frozen conditional Blender scene-generation experiment. - 50,008,320 unique parameters - dmodel: 640 - tied token embeddings / LM head [BOS] instruction [SEP] target [EOS] target + EOS Instruction and SEP positions are masked. 4293b1f043ca6875a5bc927f4e7b297cbf5b5122983effbc8cfc202494dc190e Conditional training successfully removed the unconditional output collapse observed in R2. However, semantic generation remains limited by: - object under-generation - incomplete object state - duplicate field emission - weak relation endpoint binding - invalid/self relations - location numeric collapse - long-horizon state tracking Design 3D-002-R2D addresses these problems using: - explicit object… Open weights [View model](https://savrn.com/models/design-3d-002-r2c) Model ### [designgym-sft-qwen3.6-35b-a3b-r32](https://savrn.com/models/designgym-sft-qwen3-6-35b-a3b-r32) [Adithya S K](https://savrn.com/model-publishers/adithyask) This model is a fine-tuned version of Qwen/Qwen3.6-35B-A3B. It has been trained using TRL. This model was trained with SFT. Open weights transformers [View model](https://savrn.com/models/designgym-sft-qwen3-6-35b-a3b-r32) Model ### [detr-resnet-50-dc5-fashionpedia-finetuned](https://savrn.com/models/detr-resnet-50-dc5-fashionpedia-finetuned) [Infrastructure](https://savrn.com/model-publishers/aikorven) Open weights [View model](https://savrn.com/models/detr-resnet-50-dc5-fashionpedia-finetuned) Model · Text classification ### [dev-0.4b](https://savrn.com/models/dev-0-4b) [Nikhil Pujari](https://savrn.com/model-publishers/mpnikhil) Dev is an open-source 399M parameter bidirectional decision model built on ModernBERT-large. It is purpose-built for unstructured-to-structured classification—including ticket routing, yes/no verification, and rating scales—executing in a single forward pass (~28ms on MPS) without token generation. Following Jev (TypeSafe) and Kev-0.5B (Jared Palmer), Dev tests a fundamental architectural question: What if decision models shouldn't be causal decoders at all, but native bidirectional cross-encoders? Evaluated against Jared Palmer's kev-0.5b (built on a frozen Qwen-2.5-0.5B causal backbone + 9.3M LoRA pointer head): Inference Latency: Dev-0.4B executes in 27.6ms on Apple Silicon MPS (M1 Max)… Open weights apache-2.0 397M parameters transformers [View model](https://savrn.com/models/dev-0-4b) Model ### [dev-C1b](https://savrn.com/models/dev-c1b) [Bima Bagaskhoro](https://savrn.com/model-publishers/bimabk) Open weights 1.7B parameters 32,768 tokens [View model](https://savrn.com/models/dev-c1b) Model ### [dev-D1f](https://savrn.com/models/dev-d1f) [Bima Bagaskhoro](https://savrn.com/model-publishers/bimabk) Open weights 1.7B parameters 32,768 tokens [View model](https://savrn.com/models/dev-d1f) Model ### [dev-D8off2](https://savrn.com/models/dev-d8off2) [Bima Bagaskhoro](https://savrn.com/model-publishers/bimabk) Open weights 1.7B parameters 32,768 tokens [View model](https://savrn.com/models/dev-d8off2) Model ### [dev-M26g2](https://savrn.com/models/dev-m26g2) [Bima Bagaskhoro](https://savrn.com/model-publishers/bimabk) Open weights 3.4B parameters 131,072 tokens [View model](https://savrn.com/models/dev-m26g2) ## 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.