This model was converted to MLX format from nvidia/parakeet-tdt-0.6b-v3 using the conversion script. Please refer to original model card for more details on the model.
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.
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…
[Gemma 3 Technical Report][g3-tech-report] [Responsible Generative AI Toolkit][rai-toolkit] [Gemma on Kaggle][kaggle-gemma] [Gemma on Vertex Model Garden][vertex-mg-gemma3] Summary description and brief definition of inputs and outputs. Gemma is a family of lightweight, state-of-the-art open models from Google, built from the same research and technology used to create the Gemini models. Gemma 3 models are multimodal, handling text and image input and generating text output, with open weights for both pre-trained variants and instruction-tuned variants. Gemma 3 has a large, 128K context window, multilingual support in over 140 languages, and is available in more sizes than previous…
This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the filipinovoice dataset. It achieves the following results on the evaluation set: The following hyperparameters were used during training: - learningrate: 0.0003 - trainbatchsize: 8 - evalbatchsize: 8 - gradientaccumulationsteps: 2 - totaltrainbatchsize: 16 - lrschedulertype: linear - lrschedulerwarmupsteps: 500 - numepochs: 30 - mixedprecisiontraining: Native AMP - Transformers 4.11.3 - Pytorch 1.10.0+cu113 - Datasets 1.18.3 - Tokenizers 0.10.3
Vision Transformer (ViT) model pre-trained on ImageNet-21k (14 million images, 21,843 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 transformer encoder model (BERT-like) pretrained on a large collection of images in a…
Below is the model card of Llava model 7b, which is copied from the original Llava model card that you can find here. Check out also the Google Colab demo to run Llava on a free-tier Google Colab instance: Or check out our Spaces demo! LLaVA is an open-source chatbot trained by fine-tuning LLaMA/Vicuna on GPT-generated multimodal instruction-following data. It is an auto-regressive language model, based on the transformer architecture. LLaVA-v1.5-7B was trained in September 2023. Paper or resources for more information: https://llava-vl.github.io/ First, make sure to have transformers >= 4.35.3. The model supports multi-image and multi-prompt generation. Meaning that you can pass multiple…
Modifications to the original model card are in red or green Stable Diffusion is a latent text-to-image diffusion model capable of generating photo-realistic images given any text input. For more information about how Stable Diffusion functions, please have a look at 's Stable Diffusion blog. The Stable-Diffusion-v1-5 checkpoint was initialized with the weights of the Stable-Diffusion-v1-2 checkpoint and subsequently fine-tuned on 595k steps at resolution 512x512 on "laion-aesthetics v2 5+" and 10% dropping of the text-conditioning to improve classifier-free guidance sampling. You can use this both with the Diffusers library and RunwayML GitHub repository ( now deprecated ), ComfyUI…
A EfficientNet-v2 image classification model. Trained on ImageNet-21k and fine-tuned on ImageNet-1k in Tensorflow by paper authors, ported to PyTorch by Ross Wightman. Explore the dataset and runtime metrics of this model in timm model results.
Fine-tuned facebook/wav2vec2-large-xlsr-53 on Persian using the train and validation splits of Common Voice 6.1. 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 Persian 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 evaluation script…
The Mistral-7B-Instruct-v0.2 Large Language Model (LLM) is an instruct fine-tuned version of the Mistral-7B-v0.2. Mistral-7B-v0.2 has the following changes compared to Mistral-7B-v0.1 - 32k context window (vs 8k context in v0.1) - Rope-theta = 1e6 For full details of this model please read our paper and release blog post. In order to leverage instruction fine-tuning, your prompt should be surrounded by [INST] and [/INST] tokens. The very first instruction should begin with a begin of sentence id. The next instructions should not. The assistant generation will be ended by the end-of-sentence token id. This format is available as a chat template via the applychattemplate() method: - If you…
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…
Using this open-source model in production? Consider switching to pyannoteAI for better and faster options. In order to reproduce the results of the paper "End-to-end speaker segmentation for overlap-aware resegmentation ", use pyannote/segmentation@Interspeech2021 with the following hyper-parameters: Expected outputs (and VBx baseline) are also provided in the /reproducibleresearch sub-directories.
Repackaged model files for ComfyUI. - https://huggingface.co/dx8152/Qwen-Edit-2509-Light-Migration/ - https://huggingface.co/dx8152/Qwen-Edit-2509-Multiple-angles - https://huggingface.co/dx8152/Qwen-Image-Edit-2509-Fusion - https://huggingface.co/dx8152/Qwen-Image-Edit-2509-Relight - https://huggingface.co/lrzjason/QwenEdit-Anything2RealAlpha/ Place the files in the following folders: - Qwen-Image-Edit-2509-Light-Migration.safetensors from dx8152/Qwen-Edit-2509-Light-Migration - Qwen-Edit-2509-Multiple-angles.safetensors from dx8152/Qwen-Edit-2509-Multiple-angles - Qwen-Image-Edit-2509-Relight.safetensors from dx8152/Qwen-Image-Edit-2509-Fusion - Qwen-Image-Edit-2509-Relight.safetensors…
Join our WeChat and Discord community Use GLM-OCR's API GLM-OCR is a multimodal OCR model for complex document understanding, built on the GLM-V encoder–decoder architecture. It introduces Multi-Token Prediction (MTP) loss and stable full-task reinforcement learning to improve training efficiency, recognition accuracy, and generalization. The model integrates the CogViT visual encoder pre-trained on large-scale image–text data, a lightweight cross-modal connector with efficient token downsampling, and a GLM-0.5B language decoder. Combined with a two-stage pipeline of layout analysis and parallel recognition based on PP-DocLayout-V3, GLM-OCR delivers robust and high-quality OCR performance…
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…
captioning pretrained on COCO dataset - base architecture (with ViT base backbone). Authors from the paper write in the abstract: Vision-Language Pre-training (VLP) has advanced the performance for many vision-language tasks. However, most existing pre-trained models only excel in either understanding-based tasks or generation-based tasks. Furthermore, performance improvement has been largely achieved by scaling up the dataset with noisy image-text pairs collected from the web, which is a suboptimal source of supervision. In this paper, we propose BLIP, a new VLP framework which transfers flexibly to both vision-language understanding and generation tasks. BLIP effectively utilizes the…
2.5x faster throughput than other NVFP4 quants. This is an Unsloth NVFP4 quantized checkpoint calibrated on a mixture of our Unsloth dataset + UltraChat dataset. Works on a 24GB VRAM GPU. Benchmarks on 1xB200 128 concurrency. For accuracy benchmarks, we conducted MMLU-Pro, AIME 2025, GPQA for FP8, BF16, NVIDIA's NVFP4 and our NVFP4s - we show our faster quants do similarly on all: Read all benchmarks in our NVFP4 blog To install vLLM in a separate venv: Then to serve the 27B NVFP4 quant: Also do NOT use the Marlin backend since it's 2x slower - use the native vLLM or cute-DSL / CUTLASS / flashinfertrtllm backends! You must use the below or you will get 2x slower inference! This checkpoint…
The OWLv2 model (short for Open-World Localization) was proposed in Scaling Open-Vocabulary Object Detection by Matthias Minderer, Alexey Gritsenko, Neil Houlsby. OWLv2, like OWL-ViT, is a zero-shot text-conditioned object detection model that can be used to query an image with one or multiple text queries. The model uses CLIP as its multi-modal backbone, with a ViT-like Transformer to get visual features and a causal language model to get the text features. To use CLIP for detection, OWL-ViT removes the final token pooling layer of the vision model and attaches a lightweight classification and box head to each transformer output token. Open-vocabulary classification is enabled by replacing…
A fine-tuned XLS-R 300M CTC model for Urdu automatic speech recognition. It transcribes 16 kHz mono audio and includes an optional 5-gram KenLM decoder. Best reported result: 39.89% WER / 16.70% CER with KenLM decoding on the Urdu Common Voice 8.0 test set. See the Kaggle evaluation notebook for a reproducible example. The repository contains a 5-gram KenLM language model. The Kaggle notebook evaluates a five-sample streaming smoke test from fixie-ai/commonvoice170 (ur, test). Results are reported on the Urdu test split of Mozilla Common Voice 8.0. The language-model row is the model-card score; compare each result only with the same decoding strategy. To reproduce language-model evaluation…
Whisper is a pre-trained model for automatic speech recognition (ASR) and speech translation. Trained on 680k hours of labelled data, Whisper models demonstrate a strong ability to generalise to many datasets and domains without the need for fine-tuning. Whisper was proposed in the paper Robust Speech Recognition via Large-Scale Weak Supervision by Alec Radford et al from OpenAI. The original code repository can be found here. Disclaimer: Content for this model card has partly been written by the Hugging Face team, and parts of it were copied and pasted from the original model card. Whisper is a Transformer based encoder-decoder model, also referred to as a sequence-to-sequence model. It…
This repository contains the conversion of openai/whisper-base to the CTranslate2 model format. This model can be used in CTranslate2 or projects based on CTranslate2 such as faster-whisper. The original model was converted with the following command: Note that the model weights are saved in FP16. This type can be changed when the model is loaded using the computetype option in CTranslate2. For more information about the original model, see its model card.
heron is the default layout analysis model of the Docling project, designed for robust and high-quality document layout understanding. For an in-depth description of the model architecture, training datasets, and evaluation methodology, please refer to our technical report: "Advanced Layout Analysis Models for Docling", Nikolaos Livathinos et al.
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…
Liang Wang, Nan Yang, Xiaolong Huang, Linjun Yang, Rangan Majumder, Furu Wei, arXiv 2024 This model has 24 layers and the embedding size is 1024. Below are examples to encode queries and passages from the MS-MARCO passage ranking dataset. Usage with Infinity: This model is initialized from xlm-roberta-large and continually trained on a mixture of multilingual datasets. It supports 100 languages from xlm-roberta, but low-resource languages may see performance degradation. First stage: contrastive pre-training with 1 billion weakly supervised text pairs. Check out unilm/e5 to reproduce evaluation results on the BEIR and MTEB benchmark. 1. Do I need to add instructions to the query? Yes, this…
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.