# Open-Weight AI Models: Compare Cards, Specs and Licenses Source: https://savrn.com/models 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. The SAVRN Model Hub lists open-weight models, the ones you can download and run on hardware you control. We built it because choosing a model is really three decisions made at once: what the model can do, what you are allowed to do with it, and what it costs to run. Most catalogs answer the first question and leave the other two to you. Every model page here shows the license in plain terms, the memory the weights need at 16, 8 and 4 bits, and the cheapest accelerator setup that holds them, priced from the SAVRN Index. Browse by task if you know the job, by license if commercial use is the constraint, or by publisher if you already trust a lab. The comparison pages put similar models side by side on the same facts. 12,870Models 3,655Datasets 291Papers 7,691Publishers 12,980Sourced relationships Updated 2026-10-24 · [How the library is built](https://savrn.com/model-hub/methodology) ## Filter Models Task - [Text generation1,582](https://savrn.com/models?task=Text+generation) - [Image and text to text588](https://savrn.com/models?task=Image+and+text+to+text) - [Robotics403](https://savrn.com/models?task=Robotics) - [Feature extraction400](https://savrn.com/models?task=Feature+extraction) - [Text classification335](https://savrn.com/models?task=Text+classification) - [Text to image236](https://savrn.com/models?task=Text+to+image) - [Speech recognition190](https://savrn.com/models?task=Speech+recognition) - [Text to speech148](https://savrn.com/models?task=Text+to+speech) - [Image classification140](https://savrn.com/models?task=Image+classification) - [Audio classification130](https://savrn.com/models?task=Audio+classification) - [Sentence similarity103](https://savrn.com/models?task=Sentence+similarity) - [Reinforcement learning102](https://savrn.com/models?task=Reinforcement+learning) - [Token classification101](https://savrn.com/models?task=Token+classification) - [Zero-shot classification96](https://savrn.com/models?task=Zero-shot+classification) - [Image segmentation90](https://savrn.com/models?task=Image+segmentation) - [Object detection87](https://savrn.com/models?task=Object+detection) - [Translation82](https://savrn.com/models?task=Translation) - [Any to any79](https://savrn.com/models?task=Any+to+any) - [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 classification61](https://savrn.com/models?task=Video+classification) - [Image to text60](https://savrn.com/models?task=Image+to+text) - [Text to video55](https://savrn.com/models?task=Text+to+video) Library - [transformers3,042](https://savrn.com/models?library=transformers) - [peft369](https://savrn.com/models?library=peft) - [diffusers210](https://savrn.com/models?library=diffusers) - [pytorch206](https://savrn.com/models?library=pytorch) - [gguf188](https://savrn.com/models?library=gguf) - [mlx172](https://savrn.com/models?library=mlx) - [lerobot154](https://savrn.com/models?library=lerobot) - [sentence-transformers139](https://savrn.com/models?library=sentence-transformers) - [timm49](https://savrn.com/models?library=timm) - [llama.cpp47](https://savrn.com/models?library=llama.cpp) - [transformers.js45](https://savrn.com/models?library=transformers.js) - [flaxspeaker44](https://savrn.com/models?library=flaxspeaker) - [onnx42](https://savrn.com/models?library=onnx) - [diffusion-single-file40](https://savrn.com/models?library=diffusion-single-file) - [vllm40](https://savrn.com/models?library=vllm) - [openpi35](https://savrn.com/models?library=openpi) - [minimax-h329](https://savrn.com/models?library=minimax-h3) - [ultralytics24](https://savrn.com/models?library=ultralytics) - [coreml23](https://savrn.com/models?library=coreml) - [exllamav323](https://savrn.com/models?library=exllamav3) - [PaddleOCR22](https://savrn.com/models?library=PaddleOCR) - [openvino20](https://savrn.com/models?library=openvino) - [litert17](https://savrn.com/models?library=litert) - [litert-lm16](https://savrn.com/models?library=litert-lm) Modality - [Other7,428](https://savrn.com/models?modality=Other) - [Text2,883](https://savrn.com/models?modality=Text) - [Image and text648](https://savrn.com/models?modality=Image+and+text) - [Image604](https://savrn.com/models?modality=Image) - [Control505](https://savrn.com/models?modality=Control) - [Audio487](https://savrn.com/models?modality=Audio) - [Video116](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-2.03,395](https://savrn.com/models?license=apache-2.0) - [mit1,335](https://savrn.com/models?license=mit) - [other812](https://savrn.com/models?license=other) - [cc-by-nc-4.0215](https://savrn.com/models?license=cc-by-nc-4.0) - [cc-by-4.0172](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-4.056](https://savrn.com/models?license=cc-by-nc-sa-4.0) - [llama3.240](https://savrn.com/models?license=llama3.2) - [unknown33](https://savrn.com/models?license=unknown) - [agpl-3.032](https://savrn.com/models?license=agpl-3.0) - [llama3.129](https://savrn.com/models?license=llama3.1) - [cc-by-sa-4.020](https://savrn.com/models?license=cc-by-sa-4.0) - [gpl-3.020](https://savrn.com/models?license=gpl-3.0) - [openrail++18](https://savrn.com/models?license=openrail%2B%2B) - [creativeml-openrail-m15](https://savrn.com/models?license=creativeml-openrail-m) - [openmdw-1.115](https://savrn.com/models?license=openmdw-1.1) - [cc-by-nc-nd-4.014](https://savrn.com/models?license=cc-by-nc-nd-4.0) - [llama314](https://savrn.com/models?license=llama3) - [openrail14](https://savrn.com/models?license=openrail) - [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 weights12,434](https://savrn.com/models?access=open_access) - [Access requested at publisher436](https://savrn.com/models?access=gated) Publisher - [Team Mradermacher328](https://savrn.com/models?publisher=mradermacher) - [Yurun Yuan116](https://savrn.com/models?publisher=ryanyr) - [RunningHub.ai105](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) - [Yurun Yuan66](https://savrn.com/models?publisher=yurunyyr) - [Google64](https://savrn.com/models?publisher=google) - [Yurun Yuan62](https://savrn.com/models?publisher=yuruny) - [Firza Hadzami61](https://savrn.com/models?publisher=firzahdzm) - [Christopher Subia-Waud60](https://savrn.com/models?publisher=cwaud) - [Yurun Yuan60](https://savrn.com/models?publisher=yyuan244) - [Zeyuan Yang59](https://savrn.com/models?publisher=miiche) - [Yanggangu57](https://savrn.com/models?publisher=yanggangu) - [Hongao56](https://savrn.com/models?publisher=cisco1963) - [Szekely53](https://savrn.com/models?publisher=attila115) - [Francesca Padovani53](https://savrn.com/models?publisher=francesca9805) - [Khazzz1c53](https://savrn.com/models?publisher=khazic) - [Alfred Smith52](https://savrn.com/models?publisher=alfred8995) - [NVIDIA50](https://savrn.com/models?publisher=nvidia) - [Wang49](https://savrn.com/models?publisher=davidwdw) [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) 12,870 models, sorted by most downloaded. Model · Sentence similarity ### [all-MiniLM-L6-v2](https://savrn.com/models/all-minilm-l6-v2) [Sentence Transformers](https://savrn.com/model-publishers/sentence-transformers) This is a sentence-transformers model: It maps sentences & paragraphs to a 384 dimensional dense vector space and can be used for tasks like clustering or semantic search. Using this model becomes easy when you have sentence-transformers installed: Then you can use the model like this: Without sentence-transformers, you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings. The project aims to train sentence embedding models on very large sentence level datasets using a self-supervised contrastive learning objective. We used the pretrained… Open weights apache-2.0 23M parameters 512 tokens sentence-transformers [View model](https://savrn.com/models/all-minilm-l6-v2) Model · Text ranking ### [ms-marco-MiniLM-L6-v2](https://savrn.com/models/ms-marco-minilm-l6-v2) [Sentence Transformers - Cross-Encoders](https://savrn.com/model-publishers/cross-encoder) This model was trained on the MS Marco Passage Ranking task. The model can be used for Information Retrieval: Given a query, encode the query with all possible passages (e.g. retrieved with ElasticSearch). Then sort the passages in a decreasing order. See SBERT.net Retrieve & Re-rank for more details. The training code is available here: SBERT.net Training MS Marco The usage is easy when you have SentenceTransformers installed. Then you can use the pre-trained models like this: In the following table, we provide various pre-trained Cross-Encoders together with their performance on the TREC Deep Learning 2019 and the MS Marco Passage Reranking dataset. Open weights apache-2.0 23M parameters 512 tokens sentence-transformers [View model](https://savrn.com/models/ms-marco-minilm-l6-v2) Model · Feature extraction ### [bge-small-en-v1.5](https://savrn.com/models/bge-small-en-v1-5) [Beijing Academy of Artificial Intelligence](https://savrn.com/model-publishers/baai) More details please refer to our Github: FlagEmbedding. If you are looking for a model that supports more languages, longer texts, and other retrieval methods, you can try using bge-m3. FlagEmbedding focuses on retrieval-augmented LLMs, consisting of the following projects currently: - 1/30/2024: Release BGE-M3, a new member to BGE model series! M3 stands for Multi-linguality (100+ languages), Multi-granularities (input length up to 8192), Multi-Functionality (unification of dense, lexical, multi-vec/colbert retrieval). It is the first embedding model which supports all three retrieval methods, achieving new SOTA on multi-lingual (MIRACL) and cross-lingual (MKQA) benchmarks. Technical… Open weights mit 33M parameters 512 tokens sentence-transformers [View model](https://savrn.com/models/bge-small-en-v1-5) Model · Sentence similarity ### [paraphrase-multilingual-MiniLM-L12-v2](https://savrn.com/models/paraphrase-multilingual-minilm-l12-v2) [Sentence Transformers](https://savrn.com/model-publishers/sentence-transformers) This is a sentence-transformers model: It maps sentences & paragraphs to a 384 dimensional dense vector space and can be used for tasks like clustering or semantic search. Using this model becomes easy when you have sentence-transformers installed: Then you can use the model like this: Without sentence-transformers, you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings. This model was trained by sentence-transformers. If you find this model helpful, feel free to cite our publication Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks Open weights apache-2.0 118M parameters 512 tokens sentence-transformers [View model](https://savrn.com/models/paraphrase-multilingual-minilm-l12-v2) Model ### [electra-base-discriminator](https://savrn.com/models/electra-base-discriminator) [Google](https://savrn.com/model-publishers/google) ELECTRA is a new method for self-supervised language representation learning. It can be used to pre-train transformer networks using relatively little compute. ELECTRA models are trained to distinguish "real" input tokens vs "fake" input tokens generated by another neural network, similar to the discriminator of a GAN. At small scale, ELECTRA achieves strong results even when trained on a single GPU. At large scale, ELECTRA achieves state-of-the-art results on the SQuAD 2.0 dataset. For a detailed description and experimental results, please refer to our paper ELECTRA: Pre-training Text Encoders as Discriminators Rather Than Generators. This repository contains code to pre-train ELECTRA… Open weights apache-2.0 512 tokens transformers [View model](https://savrn.com/models/electra-base-discriminator) Model · Sentence similarity ### [bge-m3](https://savrn.com/models/bge-m3) [Beijing Academy of Artificial Intelligence](https://savrn.com/model-publishers/baai) For more details please refer to our github repo: https://github.com/FlagOpen/FlagEmbedding In this project, we introduce BGE-M3, which is distinguished for its versatility in Multi-Functionality, Multi-Linguality, and Multi-Granularity. Some suggestions for retrieval pipeline in RAG We recommend to use the following pipeline: hybrid retrieval + re-ranking. - Hybrid retrieval leverages the strengths of various methods, offering higher accuracy and stronger generalization capabilities. Now, you can try to use BGE-M3, which supports both embedding and sparse retrieval. This allows you to obtain token weights (similar to the BM25) without any additional cost when generate dense embeddings. To… Open weights mit 8,194 tokens sentence-transformers [View model](https://savrn.com/models/bge-m3) Model · Fill mask ### [bert-base-uncased](https://savrn.com/models/bert-base-uncased) [BERT community](https://savrn.com/model-publishers/google-bert) Pretrained model on English language using a masked language modeling (MLM) objective. It was introduced in this paper and first released in this repository. This model is uncased: it does not make a difference between english and English. Disclaimer: The team releasing BERT did not write a model card for this model so this model card has been written by the Hugging Face team. BERT is a transformers model pretrained on a large corpus of English data in a self-supervised fashion. This means it was pretrained on the raw texts only, with no humans labeling them in any way (which is why it can use lots of publicly available data) with an automatic process to generate inputs and labels from… Open weights apache-2.0 110M parameters 512 tokens transformers [View model](https://savrn.com/models/bert-base-uncased) Model ### [MiniMax-H3](https://savrn.com/models/minimax-h3) [Comfy Org](https://savrn.com/model-publishers/comfy-org) Repackaged model files for ComfyUI. - https://huggingface.co/MiniMaxAI/MiniMax-H3 - https://huggingface.co/lightx2v/Minimax-h3-Turbo - https://huggingface.co/alibaba-pai/MiniMax-H3-Fun-Controlnet-Union - https://huggingface.co/Kijai/MiniMax-H3-experimental The Qwen3-VL-32B nvfp4awq quant is converted from: https://huggingface.co/cybermotaz/Qwen3-VL-32B-Instruct-NVFP4 This nvfp4 text encoder does not require Blackwell GPU to use. For diffusion models prefer int8convrot if you are able to use pytorch with cu130. fp8scaled should only be used if you cannot use int8convrot. Place the files in the following folders: To use the embeddings in a text prompt, invoke them in the CLIPTextEncode node… Open weights other diffusion-single-file [View model](https://savrn.com/models/minimax-h3) Model · Text generation ### [Qwen3-0.6B](https://savrn.com/models/qwen3-0-6b) [Qwen](https://savrn.com/model-publishers/qwen) Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models. Built upon extensive training, Qwen3 delivers groundbreaking advancements in reasoning, instruction-following, agent capabilities, and multilingual support, with the following key features: - Uniquely support of seamless switching between thinking mode (for complex logical reasoning, math, and coding) and non-thinking mode (for efficient, general-purpose dialogue) within single model, ensuring optimal performance across various scenarios. - Significantly enhancement in its reasoning capabilities, surpassing previous QwQ (in thinking mode) and… Open weights apache-2.0 752M parameters 40,960 tokens transformers [View model](https://savrn.com/models/qwen3-0-6b) Model · Translation ### [t5-small](https://savrn.com/models/t5-small) [T5 community](https://savrn.com/model-publishers/google-t5) The developers of the Text-To-Text Transfer Transformer (T5) write: T5-Small is the checkpoint with 60 million parameters. The developers write in a blog post that the model: See the blog post and research paper for further details. The model is pre-trained on the Colossal Clean Crawled Corpus (C4), which was developed and released in the context of the same research paper as T5. The model was pre-trained on a on a multi-task mixture of unsupervised (1.) and supervised tasks (2.). Thereby, the following datasets were being used for (1.) and (2.): 1. Datasets used for Unsupervised denoising objective: 2. Datasets used for Supervised text-to-text language modeling objective - CoLA Warstadt et… Open weights apache-2.0 61M parameters transformers [View model](https://savrn.com/models/t5-small) Model · Text generation ### [gpt2](https://savrn.com/models/gpt2) [OpenAI community](https://savrn.com/model-publishers/openai-community) Test the whole generation capabilities here: https://transformer.huggingface.co/doc/gpt2-large Pretrained model on English language using a causal language modeling (CLM) objective. It was introduced in and first released at this page. model. Content from this model card has been written by the Hugging Face team to complete the information they provided and give specific examples of bias. GPT-2 is a transformers model pretrained on a very large corpus of English data in a self-supervised fashion. This means it was pretrained on the raw texts only, with no humans labelling them in any way (which is why it can use lots of publicly available data) with an automatic process to generate inputs… Open weights mit 137M parameters transformers [View model](https://savrn.com/models/gpt2) Model · Sentence similarity ### [all-mpnet-base-v2](https://savrn.com/models/all-mpnet-base-v2) [Sentence Transformers](https://savrn.com/model-publishers/sentence-transformers) This is a sentence-transformers model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search. Using this model becomes easy when you have sentence-transformers installed: Then you can use the model like this: Without sentence-transformers, you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings. Text Embeddings Inference (TEI) is a blazing fast inference solution for text embedding models. Send a request to /v1/embeddings to generate embeddings via the OpenAI Embeddings API: Or check… Open weights apache-2.0 109M parameters 514 tokens sentence-transformers [View model](https://savrn.com/models/all-mpnet-base-v2) Model · Image classification ### [mobilenetv3_small_100.lamb_in1k](https://savrn.com/models/mobilenetv3-small-100-lamb-in1k) [PyTorch Image Models](https://savrn.com/model-publishers/timm) A MobileNet-v3 image classification model. Trained on ImageNet-1k in timm using recipe template described below. A LAMB optimizer based recipe that is similar to ResNet Strikes Back A2 but 50% longer with EMA weight averaging, no CutMix Step (exponential decay w/ staircase) LR schedule with warmup Explore the dataset and runtime metrics of this model in timm model results. Open weights apache-2.0 3M parameters timm [View model](https://savrn.com/models/mobilenetv3-small-100-lamb-in1k) Model · Zero shot image classification ### [clip-vit-base-patch32](https://savrn.com/models/clip-vit-base-patch32) [OpenAI](https://savrn.com/model-publishers/openai) Disclaimer: The model card is taken and modified from the official CLIP repository, it can be found here. The CLIP model was developed by researchers at OpenAI to learn about what contributes to robustness in computer vision tasks. The model was also developed to test the ability of models to generalize to arbitrary image classification tasks in a zero-shot manner. It was not developed for general model deployment - to deploy models like CLIP, researchers will first need to carefully study their capabilities in relation to the specific context they’re being deployed within. January 2021 The model uses a ViT-B/32 Transformer architecture as an image encoder and uses a masked self-attention… Open weights 77 tokens transformers [View model](https://savrn.com/models/clip-vit-base-patch32) Model · Speech recognition ### [wav2vec2-large-xlsr-53-japanese](https://savrn.com/models/wav2vec2-large-xlsr-53-japanese) [Jonatas Grosman](https://savrn.com/model-publishers/jonatasgrosman) Fine-tuned facebook/wav2vec2-large-xlsr-53 on Japanese using the train and validation splits of Common Voice 6.1, CSS10 and JSUT. When using this model, make sure that your speech input is sampled at 16kHz. This model has been fine-tuned thanks to the GPU credits generously given by the OVHcloud:) The script used for training can be found here: https://github.com/jonatasgrosman/wav2vec2-sprint The model can be used directly (without a language model) as follows... Using the HuggingSound library: The model can be evaluated as follows on the Japanese test data of Common Voice. In the table below I report the Word Error Rate (WER) and the Character Error Rate (CER) of the model. I ran the… Open weights apache-2.0 transformers [View model](https://savrn.com/models/wav2vec2-large-xlsr-53-japanese) Model · Text classification ### [bge-reranker-v2-m3](https://savrn.com/models/bge-reranker-v2-m3) [Beijing Academy of Artificial Intelligence](https://savrn.com/model-publishers/baai) More details please refer to our Github: FlagEmbedding. Different from embedding model, reranker uses question and document as input and directly output similarity instead of embedding. You can get a relevance score by inputting query and passage to the reranker. And the score can be mapped to a float value in [0,1] by sigmoid function. You can select the model according your senario and resource. - For multilingual, utilize BAAI/bge-reranker-v2-m3 and BAAI/bge-reranker-v2-gemma - For Chinese or English, utilize BAAI/bge-reranker-v2-m3 and BAAI/bge-reranker-v2-minicpm-layerwise. - For efficiency, utilize BAAI/bge-reranker-v2-m3 and the low layer of BAAI/bge-reranker-v2-minicpm-layerwise.… Open weights apache-2.0 568M parameters 8,194 tokens sentence-transformers [View model](https://savrn.com/models/bge-reranker-v2-m3) Model · Time series forecasting ### [chronos-2](https://savrn.com/models/chronos-2) [Amazon](https://savrn.com/model-publishers/amazon) Update Jun 5, 2026: Deploy Chronos-2 on AWS with AutoGluon-Cloud. Real-time, serverless, or batch inference in 3 lines of code — pandas DataFrames in, forecasts out. Check out the new deployment guide. Chronos-2 is a 120M-parameter, encoder-only time series foundation model for zero-shot forecasting. It supports univariate, multivariate, and covariate-informed tasks within a single architecture. Inspired by the T5 encoder, Chronos-2 produces multi-step-ahead quantile forecasts and uses a group attention mechanism for efficient in-context learning across related series and covariates. Trained on a combination of real-world and large-scale synthetic datasets, it achieves state-of-the-art… Open weights apache-2.0 119M parameters chronos-forecasting [View model](https://savrn.com/models/chronos-2) Model · Image classification ### [vit-base-patch16-224](https://savrn.com/models/vit-base-patch16-224) [Google](https://savrn.com/model-publishers/google) Vision Transformer (ViT) model pre-trained on ImageNet-21k (14 million images, 21,843 classes) at resolution 224x224, and fine-tuned on ImageNet 2012 (1 million images, 1,000 classes) at resolution 224x224. It was introduced in the paper An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale by Dosovitskiy et al. and first released in this repository. However, the weights were converted from the timm repository by Ross Wightman, who already converted the weights from JAX to PyTorch. Credits go to him. Disclaimer: The team releasing ViT did not write a model card for this model so this model card has been written by the Hugging Face team. The Vision Transformer (ViT) is a… Open weights apache-2.0 87M parameters transformers [View model](https://savrn.com/models/vit-base-patch16-224) Model · Time series forecasting ### [chronos-2](https://savrn.com/models/chronos-2-2) [Autogluon](https://savrn.com/model-publishers/autogluon) Update Jun 5, 2026: Deploy Chronos-2 on AWS with AutoGluon-Cloud. Real-time, serverless, or batch inference in 3 lines of code — pandas DataFrames in, forecasts out. Check out the new deployment guide. Chronos-2 is a 120M-parameter, encoder-only time series foundation model for zero-shot forecasting. It supports univariate, multivariate, and covariate-informed tasks within a single architecture. Inspired by the T5 encoder, Chronos-2 produces multi-step-ahead quantile forecasts and uses a group attention mechanism for efficient in-context learning across related series and covariates. Trained on a combination of real-world and large-scale synthetic datasets, it achieves state-of-the-art… Open weights apache-2.0 119M parameters chronos-forecasting [View model](https://savrn.com/models/chronos-2-2) Model · Sentence similarity ### [nomic-embed-text-v1.5](https://savrn.com/models/nomic-embed-text-v1-5) [Nomic AI](https://savrn.com/model-publishers/nomic-ai) Exciting Update!: nomic-embed-text-v1.5 is now multimodal! nomic-embed-vision-v1.5 is aligned to the embedding space of nomic-embed-text-v1.5, meaning any text embedding is multimodal! Important: the text prompt must include a task instruction prefix, instructing the model which task is being performed. For example, if you are implementing a RAG application, you embed your documents as searchdocument: and embed your user queries as searchquery:. Notice: From transformers v5.5.0 and sentence transformers v5.3.0, trustremotecode=True will no longer be necessary. This will only be possible with the text-only series as of now. This prefix is used for embedding texts as documents, for example as… Open weights apache-2.0 137M parameters 2,048 tokens sentence-transformers [View model](https://savrn.com/models/nomic-embed-text-v1-5) Model · Speech recognition ### [whisperkit-coreml](https://savrn.com/models/whisperkit-coreml) [Argmax](https://savrn.com/model-publishers/argmaxinc) WhisperKit is part of Argmax OSS, an On-device Speech AI SDK for Apple Silicon: https://github.com/argmaxinc/argmax-oss-swift Check out the WhisperKit paper and presentation from ICML 2025: https://icml.cc/virtual/2025/47854 For real-time transcription with speakers and custom vocabulary, check out Argmax Pro SDK: https://www.argmaxinc.com/blog/argmax-sdk-2 Open weights mit whisperkit [View model](https://savrn.com/models/whisperkit-coreml) Model · Text generation ### [Qwen3-4B](https://savrn.com/models/qwen3-4b) [Qwen](https://savrn.com/model-publishers/qwen) Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models. Built upon extensive training, Qwen3 delivers groundbreaking advancements in reasoning, instruction-following, agent capabilities, and multilingual support, with the following key features: - Uniquely support of seamless switching between thinking mode (for complex logical reasoning, math, and coding) and non-thinking mode (for efficient, general-purpose dialogue) within single model, ensuring optimal performance across various scenarios. - Significantly enhancement in its reasoning capabilities, surpassing previous QwQ (in thinking mode) and… Open weights apache-2.0 4B parameters 40,960 tokens transformers [View model](https://savrn.com/models/qwen3-4b) Model · Text to speech ### [Kokoro-82M](https://savrn.com/models/kokoro-82m) [Hexgrad](https://savrn.com/model-publishers/hexgrad) Kokoro is an open-weight TTS model with 82 million parameters. Despite its lightweight architecture, it delivers comparable quality to larger models while being significantly faster and more cost-efficient. With Apache-licensed weights, Kokoro can be deployed anywhere from production environments to personal projects. You can run this basic cell on Google Colab. Listen to samples. For more languages and details, see Advanced Usage. Under the hood, kokoro uses misaki, a G2P library at https://github.com/hexgrad/misaki Model SHA256 Hash: 496dba118d1a58f5f3db2efc88dbdc216e0483fc89fe6e47ee1f2c53f18ad1e4 Data: Kokoro was trained exclusively on permissive/non-copyrighted audio data and IPA… Open weights apache-2.0 [View model](https://savrn.com/models/kokoro-82m) Model ### [Qwen-Image-2.1](https://savrn.com/models/qwen-image-2-1) [Comfy Org](https://savrn.com/model-publishers/comfy-org) Repackaged model files for ComfyUI. - https://huggingface.co/Qwen/Qwen-Image-2.1 - https://huggingface.co/Qwen/Qwen-Image-2.1-Turbo The qwen3.59bqwenimage2.1pe models are for prompt enhancement, to be used with the Generate Text node. - https://huggingface.co/Qwen/Qwen-Image-2.1-PE-T2I - https://huggingface.co/Qwen/Qwen-Image-2.1-PE-I2I For faster inference, use either the full Turbo model, or the Turbo LoRA extracted from the base model. Use 8 steps and cfg 1. Place the files in the following folders Open weights other diffusion-single-file [View model](https://savrn.com/models/qwen-image-2-1) Explore more models ## Models by Task - [Text Generation](https://savrn.com/models/tasks/text-generation) 1582 - [Image and Text to Text](https://savrn.com/models/tasks/image-and-text-to-text) 588 - [Robotics](https://savrn.com/models/tasks/robotics) 403 - [Feature Extraction](https://savrn.com/models/tasks/feature-extraction) 400 - [Text Classification](https://savrn.com/models/tasks/text-classification) 335 - [Text to Image](https://savrn.com/models/tasks/text-to-image) 236 - [Speech Recognition](https://savrn.com/models/tasks/speech-recognition) 190 - [Text to Speech](https://savrn.com/models/tasks/text-to-speech) 148 - [Image Classification](https://savrn.com/models/tasks/image-classification) 140 - [Audio Classification](https://savrn.com/models/tasks/audio-classification) 130 - [Sentence Similarity](https://savrn.com/models/tasks/sentence-similarity) 103 - [Reinforcement Learning](https://savrn.com/models/tasks/reinforcement-learning) 102 - [Token Classification](https://savrn.com/models/tasks/token-classification) 101 - [Zero-Shot Classification](https://savrn.com/models/tasks/zero-shot-classification) 96 - [Image Segmentation](https://savrn.com/models/tasks/image-segmentation) 90 - [Object Detection](https://savrn.com/models/tasks/object-detection) 87 - [Translation](https://savrn.com/models/tasks/translation) 82 - [Any to Any](https://savrn.com/models/tasks/any-to-any) 79 - [Question Answering](https://savrn.com/models/tasks/question-answering) 73 - [Fill Mask](https://savrn.com/models/tasks/fill-mask) 69 - [Time Series Forecasting](https://savrn.com/models/tasks/time-series-forecasting) 64 - [Video Classification](https://savrn.com/models/tasks/video-classification) 61 - [Image to Text](https://savrn.com/models/tasks/image-to-text) 60 - [Text to Video](https://savrn.com/models/tasks/text-to-video) 55 - [Image to Image](https://savrn.com/models/tasks/image-to-image) 51 - [Tabular Classification](https://savrn.com/models/tasks/tabular-classification) 45 - [Summarization](https://savrn.com/models/tasks/summarization) 42 - [Image to Video](https://savrn.com/models/tasks/image-to-video) 36 - [Image Text to Image](https://savrn.com/models/tasks/image-text-to-image) 33 - [Text Ranking](https://savrn.com/models/tasks/text-ranking) 32 [See all](https://savrn.com/models/tasks) ## Models by License - [apache-2.0](https://savrn.com/models/licenses/apache-2-0) 3395 - [mit](https://savrn.com/models/licenses/mit) 1335 - [cc-by-nc-4.0](https://savrn.com/models/licenses/cc-by-nc-4-0) 215 - [cc-by-4.0](https://savrn.com/models/licenses/cc-by-4-0) 172 - [bsd-3-clause](https://savrn.com/models/licenses/bsd-3-clause) 108 - [gemma](https://savrn.com/models/licenses/gemma) 63 - [cc-by-nc-sa-4.0](https://savrn.com/models/licenses/cc-by-nc-sa-4-0) 56 - [llama3.2](https://savrn.com/models/licenses/llama3-2) 40 - [unknown](https://savrn.com/models/licenses/unknown) 33 - [agpl-3.0](https://savrn.com/models/licenses/agpl-3-0) 32 - [llama3.1](https://savrn.com/models/licenses/llama3-1) 29 - [cc-by-sa-4.0](https://savrn.com/models/licenses/cc-by-sa-4-0) 20 [See all](https://savrn.com/models/licenses) ## 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.