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.
2,760Models
859Datasets
254Papers
1,692Publishers
5,040Sourced relationships
Updated 2026-09-18 · How the library is built
2,760 models, sorted by most downloaded.
The D-FINE model was proposed in D-FINE: Redefine Regression Task in DETRs as Fine-grained Distribution Refinement by Yansong Peng, Hebei Li, Peixi Wu, Yueyi Zhang, Xiaoyan Sun, Feng Wu This model was contributed by VladOS95-cyber with the help of @qubvel-hf This is the HF transformers implementation for D-FINE coco -> model trained on COCO obj365 -> model trained on Object365 obj2coco -> model trained on Object365 and then finetuned on COCO D-FINE, a powerful real-time object detector that achieves outstanding localization precision by redefining the bounding box regression task in DETR models. D-FINE comprises two key components: Fine-grained Distribution Refinement (FDR) and Global…
X-CLIP model (base-sized, patch resolution of 16) trained fully-supervised on Kinetics-400. It was introduced in the paper Expanding Language-Image Pretrained Models for General Video Recognition by Ni et al. and first released in this repository. This model was trained using 8 frames per video, at a resolution of 224x224. Disclaimer: The team releasing X-CLIP did not write a model card for this model so this model card has been written by the Hugging Face team. X-CLIP is a minimal extension of CLIP for general video-language understanding. The model is trained in a contrastive way on (video, text) pairs. This allows the model to be used for tasks like zero-shot, few-shot or fully…
accuracy pipelinetag: tabular-classification - biology
This model is Rex-Omni, a 3B-parameter Multimodal Large Language Model (MLLM) presented in the paper "Detect Anything via Next Point Prediction". It is compatible with the Hugging Face transformers library and is licensed under the IDEA License 1.0. src="https://img.shields.io/badge/RexOmni-Website-BADFDB?style=flat-square&logo=deno&logoColor=violet&color=BADFDB" alt="RexThinker Website" src="https://img.shields.io/badge/RexOmni-Paper-Red%25red?logo=arxiv&logoColor=red&color=yellow" alt="RexThinker Paper on arXiv" src="https://img.shields.io/badge/RexOmni-Weight-orange?logo=huggingface&logoColor=yellow" alt="RexThinker weight on Hugging Face"…
This repository provides all the necessary tools to extract speaker embeddings with a pretrained TDNN model using SpeechBrain. The system is trained on Voxceleb 1+ Voxceleb2 training data. For a better experience, we encourage you to learn more about SpeechBrain. The given model performance on Voxceleb1-test set (Cleaned) is: This system is composed of a TDNN model coupled with statistical pooling. The system is trained with Categorical Cross-Entropy Loss. First of all, please install SpeechBrain with the following command: Please notice that we encourage you to read our tutorials and learn more about The system is trained with recordings sampled at 16kHz (single channel). The code will…
VideoMAEv2-Base model pre-trained for 800 epochs in a self-supervised way on UnlabeldHybrid-1M dataset. It was introduced in the paper [[CVPR23]VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking](https://arxiv.org/abs/2203.12602) by Wang et al. and first released in GitHub. You can use the raw model for video feature extraction. Here is how to use this model to extract a video feature
Fastino-Nemotron-3.5-Lightning-Finance is a 30B-parameter, 3B-active mixture-of-experts model specialized for financial reasoning, extraction, and research fine-tuned on LoRA with the Fastino Fine-Tuning Agent. The model targets financial document reasoning, numerical question answering over filings and tables, numeric span extraction, financial entity recognition, conversational analysis, and source-grounded financial research. The evaluation suite includes FinQA, TAT-QA, SEC-Num, FinEntity, BizFinBench, BigFinanceBench, ConvFinQA, and FiQA. The published weights are BF16 and require about 66 GB before runtime overhead. An 80 GB or larger GPU, or tensor parallelism across multiple GPUs, is…
A fast and efficient ~1.5B model optimized for CPU inference. The model was refactored with BitNet features and an updated tokenizer that includes new Routing, Tool call, and Robotics tags. Built on a redesigned DeepSeek R1 architecture with native ternary (BitNet-style) support and ready-to-run GGUF quantizations. - JiRack is a cloud-ready model that helps save money on cloud infrastructure. It can be used as an expert model in RAG deployments, with the ONNX JiRack Java server as an alternative. - Benefits high quality CPU inference TQ2 on Llama.cpp and Ollama via QAT - Robotcs, Routing, Coding, Multimedia, Advanced tool calling via CMSManhattan/JiRackPrecisionTokenizer - We are working to…
ComfyUI Ultralytics Integration – Midnight1111 Model Collection For ComfyUI, here’s how to load these models: 1. Locate your ComfyUI folder (e.g. ~/ComfyUI/ or C:\ComfyUI\). 2. Create directories: 3. Place your.pt files: • Segmentation → models/ultralytics/segm/ • Detection (bbox) → models/ultralytics/bbox/ 5. In the UI: Add Node → Model → Ultralytics → choose segm/… or bbox/…. Connect an Image Loader → Ultralytics node → Previewer Unsafe files Since getattr is classified as a dangerous pickle function, any segmentation model that uses it is classified as unsafe. All models were created and saved using the official Ultralytics library, so it’s safe to use files downloaded from a trusted…
The 1.1 release introduces long period normalisation, a method applied solely during inference. This specific version (1.1-gifteval) includes the 1.1 improvements plus the pretraining dataset has been cleaned to remove overlaps with the GIFT-Eval test dataset. TiRex is a time-series foundation model designed for time series forecasting, with the emphasis to provide state-of-the-art forecasts for both short- and long-term forecasting horizon. TiRex is 35M parameter small and is based on the xLSTM architecture allowing fast and performant forecasts. The model is described in the paper TiRex: Zero-Shot Forecasting across Long and Short Horizons with Enhanced In-Context Learning. TiRex performs…
This model was trained using SentenceTransformers Cross-Encoder class. The model was trained on the SNLI and MultiNLI datasets. For a given sentence pair, it will output three scores corresponding to the labels: contradiction, entailment, neutral. For evaluation results, see SBERT.net - Pretrained Cross-Encoder. Pre-trained models can be used like this: You can use the model also directly with Transformers library (without SentenceTransformers library): This model can also be used for zero-shot-classification
The D-FINE model was proposed in D-FINE: Redefine Regression Task in DETRs as Fine-grained Distribution Refinement by Yansong Peng, Hebei Li, Peixi Wu, Yueyi Zhang, Xiaoyan Sun, Feng Wu This model was contributed by VladOS95-cyber with the help of @qubvel-hf This is the HF transformers implementation for D-FINE coco -> model trained on COCO obj365 -> model trained on Object365 obj2coco -> model trained on Object365 and then finetuned on COCO D-FINE, a powerful real-time object detector that achieves outstanding localization precision by redefining the bounding box regression task in DETR models. D-FINE comprises two key components: Fine-grained Distribution Refinement (FDR) and Global…
A compact Qwen3.5 0.8B repository with a practical GGUF quantization ladder for local inference. This card describes what is present in the repository. The public files do not document the fine-tuning dataset or provide evaluation results, so the Cyber label should be read as the repository variant name—not as a verified capability claim. With a recent llama.cpp build: The repository includes a BF16 mmproj file and its configuration includes vision components. That establishes that a projector artifact is present; it does not establish that the end-to-end multimodal path was validated for this release. Verify image input locally before depending on it. - Local experimentation with a small…
Model · Zero-shot classification
routing_module_action_question_conversation_move_hack_debertav3_nli
MolmoAct2 is an open vision-language-action model for robot control. It builds on Molmo2-ER and attaches a flow-matching continuous action expert that conditions on the VLM key-value cache through a per-layer connection. This checkpoint is fine-tuned on the full LIBERO training mixture, combining Spatial, Object, Goal, and Long suites. It is intended for both further fine-tuning and LIBERO policy inference. Use this checkpoint for LIBERO inference or for further fine-tuning. Dataset normalization metadata is stored in normstats.json. pass normtag="libero" at inference time. Continuous action prediction is the intended and recommended inference mode. Discrete action prediction is exposed for…
SmolVLA is a compact, efficient vision-language-action model that achieves competitive performance at reduced computational costs and can be deployed on consumer-grade hardware. 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.
https://huggingface.co/hustvl/yolos-tiny 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: 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).
Multi-Scale Efficient Global Context Vision Transformer (MS-EffGCViT) is a hybrid CNN-ViT architecture for deepfake detection. It fuses CNN-driven spatial inductive bias with hierarchical global-context attention to catch both local artifacts (textures, blending seams) and global artifacts (lighting, structural inconsistency). A single architecture ships in two sizes and three domain-tuned checkpoints, working on both static images and video at the frame level. - Frame-level — one model handles both images and videos (frame-level inference + aggregation). - Cross-domain — robust on both East-Asian (KoDF) and Western (Celeb-DF-v2, FaceForensics++) faces. - Two variants — Fast (b0) for…
Flash Vision-Language-Action Inference for Autonomous Driving DFlash draft model for z-lab/Alpamayo-1.5-10B, used by FlashDrive to accelerate the chain-of-causation reasoning of Alpamayo 1.5. DFlash (ICML 2026) uses a lightweight block-diffusion draft to propose several tokens in parallel; the target verifies each block in a single forward, preserving its output distribution. This draft is a 2-layer Qwen3-style network (block size 8) conditioned on target hidden states from layers 24/30/31/32/34. The repository also ships maskembedding.pt, the trained mask-token embedding FlashDrive appends to the target's embedding table. See the base model card and the FlashDrive repository for the full…
This is a ported version of The base model is hubert-large-ll60k, which is pretrained on 16kHz sampled speech audio. When using the model make sure that your speech input is also sampled at 16Khz. For more information refer to SUPERB: Speech processing Universal PERformance Benchmark Emotion Recognition (ER) predicts an emotion class for each utterance. The most widely used ER dataset IEMOCAP is adopted, and we follow the conventional evaluation protocol: we drop the unbalanced emotion classes to leave the final four classes with a similar amount of data points and cross-validate on five folds of the standard splits. For the original model's training and evaluation instructions refer to the…
This model can be used for the task of Question Answering on Legal Documents. Read: An Open Source Contractual Language Understanding Application Using Machine Learning for detailed information on training procedure, dataset preprocessing and evaluation. See CUAD dataset card for more information. See CUAD dataset card for more information. Used V100/P100 from Google Colab Pro Python, Transformers Mohammed Rakib in collaboration with Ezi Ozoani and the Hugging Face team Use the code below to get started with the model.
π₀.₅ is a Vision-Language-Action (VLA) model with open-world generalization from Physical Intelligence, co-trained on robot demonstrations and large-scale multimodal data to execute long-horizon tasks in unseen real-world environments. Note: This model currently supports only the flow-matching action head for π₀.₅ training and inference. Other components from the original work (e.g., subtask prediction, action tokenization, or RL) were not released upstream and are not included here, though the LeRobot team is actively working to support them. Original paper: π0.5: A Vision-Language-Action Model with Open-World Generalization For full installation details (including optional video…
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.