Pretrained model on English language using a masked language modeling (MLM) and next sentence prediction (NSP) objective. It was introduced in this paper and first released in this repository. This model is cased: it makes a difference between english and English. The model achieves 0.58 accuracy on MLM objective and 0.80 on NSP objective. FNet is a transformers model with attention replaced with fourier transforms. Hence, the inputs do not contain an attentionmask. It is 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 labelling them in any way (which is why it can use lots of publicly available…
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.
Qwen2.5-Coder is the latest series of Code-Specific Qwen large language models (formerly known as CodeQwen). As of now, Qwen2.5-Coder has covered six mainstream model sizes, 0.5, 1.5, 3, 7, 14, 32 billion parameters, to meet the needs of different developers. Qwen2.5-Coder brings the following improvements upon CodeQwen1.5: - Significantly improvements in code generation, code reasoning and code fixing. Base on the strong Qwen2.5, we scale up the training tokens into 5.5 trillion including source code, text-code grounding, Synthetic data, etc. Qwen2.5-Coder-32B has become the current state-of-the-art open-source codeLLM, with its coding abilities matching those of GPT-4o. - A more…
Model · Image and text to text
gemma-3-27b-it-GPTQ-4b-128g
This model was obtained by quantizing the weights of gemma-3-27b-it to INT4 data type. This optimization reduces the number of bits per parameter from 16 to 4, reducing the disk size and GPU memory requirements by approximately 75%. Only the weights of the linear operators within languagemodel transformers blocks are quantized. Vision model and multimodal projection are kept in original precision. Weights are quantized using a symmetric per-group scheme, with group size 128. The GPTQ algorithm is applied for quantization. Model checkpoint is saved in compressedtensors format. This model was evaluated on the OpenLLM v1 benchmarks. Model outputs were generated with the vLLM engine. The…
This model was trained using SentenceTransformers Cross-Encoder class. This model is based on microsoft/deberta-v3-base 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 futher 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
Tiel is the fast coder of the arsenal. At 4-bit quantization and 23 GB it fixes real codebase issues at the rate (and speed, with the right GPU) of Opus 4.6 medium, while holding the best multi-turn conversation of any local model we have measured. It is also cheerfully bad at trivia. Pick it for work. Pick something else for exams. Where it sits against the other local builds Multi-turn conversation Reasoning and knowledge Where it stands. On 25 SWE-bench-Live problems Tiel fixes 12 — the same as Opus 4.6 (medium), four more than Ornith-1.5 itself, three more than Nail, and four more than Sonnet 5 (medium). Among models of its own class it is first; the ones ahead are dense 27Bs and Opus…
dots.ocr: Multilingual Document Layout Parsing in a Single Vision-Language Model dots.ocr is a powerful, multilingual document parser that unifies layout detection and content recognition within a single vision-language model while maintaining good reading order. Despite its compact 1.7B-parameter LLM foundation, it achieves state-of-the-art(SOTA) performance. 1. Powerful Performance: dots.ocr achieves SOTA performance for text, tables, and reading order on OmniDocBench, while delivering formula recognition results comparable to much larger models like Doubao-1.5 and gemini2.5-pro. 2. Multilingual Support: dots.ocr demonstrates robust parsing capabilities for low-resource languages…
For more details on how to deploy and use the model - see the Quick Start Guide below! The post-training data has a cutoff date of February 2026. The pre-training data has a cutoff date of June 2025. NVIDIA Nemotron™ is a family of open models with open weights, training data, and recipes, delivering leading efficiency and accuracy for building specialized AI agents. Nemotron-3-Super-120B-A12B-NVFP4 is a large language model (LLM) trained by NVIDIA, designed to deliver strong agentic, reasoning, and conversational capabilities. It is optimized for collaborative agents and high-volume workloads such as IT ticket automation. Like other models in the family, it responds to user queries and…
GPT-NeoX-20B is a 20 billion parameter autoregressive language model trained on the Pile using the GPT-NeoX library. Its architecture intentionally resembles that of GPT-3, and is almost identical to that of GPT-J- 6B. Its training dataset contains a multitude of English-language texts, reflecting the general-purpose nature of this model. See the accompanying paper for details about model architecture (including how it differs from GPT-3), training procedure, and additional evaluations. Model](https://arxiv.org/abs/2204.06745). For details about the training dataset, see the Pile paper, and its data sheet. Discord](https://discord.gg/zBGx3azzUn), and post them in #release-discussion. Please…
FLUX.1 [schnell] is a 12 billion parameter rectified flow transformer capable of generating images from text descriptions. For more information, please read our blog post. 1. Cutting-edge output quality and competitive prompt following, matching the performance of closed source alternatives. 2. Trained using latent adversarial diffusion distillation, FLUX.1 [schnell] can generate high-quality images in only 1 to 4 steps. 3. Released under the apache-2.0 licence, the model can be used for personal, scientific, and commercial purposes. We provide a reference implementation of FLUX.1 [schnell], as well as sampling code, in a dedicated github repository. Developers and creatives looking to…
Qwen2.5 is the latest series of Qwen large language models. For Qwen2.5, we release a number of base language models and instruction-tuned language models ranging from 0.5 to 72 billion parameters. Qwen2.5 brings the following improvements upon Qwen2: - Significantly more knowledge and has greatly improved capabilities in coding and mathematics, thanks to our specialized expert models in these domains. - Significant improvements in instruction following, generating long texts (over 8K tokens), understanding structured data (e.g, tables), and generating structured outputs especially JSON. More resilient to the diversity of system prompts, enhancing role-play implementation and…
As the frontier of foundation models pushes toward ever-larger parameter counts and ever-longer context windows, the question is no longer just how much we can scale, but how efficiently we can do so. Sustainable progress toward artificial general intelligence (AGI) that benefits everyone demands architectural innovation. Today, we are sharing a concrete step in that direction: Qwen3.8-Flash-Next. This experimental preview of the architecture that will underpin Qwen4 is built around a fundamental rethinking of how the core components of modern large language models (LLMs) interact at scale. The first open-weight release under this architecture is Qwen3.8-Flash-Next, which introduces: For…
News (May 2023): please switch to e5-base-v2, which has better performance and same method of usage. Liang Wang, Nan Yang, Xiaolong Huang, Binxing Jiao, Linjun Yang, Daxin Jiang, Rangan Majumder, Furu Wei, arXiv 2022 This model has 12 layers and the embedding size is 768. Below is an example to encode queries and passages from the MS-MARCO passage ranking dataset. Please refer to our paper at https://arxiv.org/pdf/2212.03533.pdf. Check out unilm/e5 to reproduce evaluation results on the BEIR and MTEB benchmark. Below is an example for usage with sentencetransformers. Package requirements pip install sentencetransformers~=2.2.2 1. Do I need to add the prefix "query: " and "passage: " to…
AssistantPepe8B / mobile stacking / Click here for TL;DR This is a project that was a long time in the making because I wanted to get it right. I'm still not fully satisfied, as there are some rough corners to sand, but for now, this would do. The goal was to maximize shitpostness along with helpfulness, without glazing the user for every retarded idea. Not an easy needle to thread. This amphibious AI has learned the ways of /g/, and speaks fluent brainrot, but will also help you out with just about anything you'll need, and won't be ashamed to roast you while at it. For those who remember OniMitsubishi12B - it was so overtly toxic that it made me worry at first (only to quickly be verified…
September 2025 \- December 2025 The post-training data has a cutoff date of November 28, 2025\. The pre-training data has a cutoff date of June 25, 2025\. Nemotron-3-Nano-30B-A3B-BF16 is a large language model (LLM) trained from scratch by NVIDIA, and designed as a unified model for both reasoning and non-reasoning tasks. It responds to user queries and tasks by first generating a reasoning trace and then concluding with a final response. The model's reasoning capabilities can be configured through a flag in the chat template. If the user prefers the model to provide its final answer without intermediate reasoning traces, it can be configured to do so, albeit with a slight decrease in…
A EfficientNet image classification model. Trained on ImageNet-1k in timm using recipe template described below. RandAugment RA recipe. Inspired by and evolved from EfficientNet RandAugment recipes. Published as B recipe in ResNet Strikes Back. RMSProp (TF 1.0 behaviour) optimizer, EMA weight averaging Step (exponential decay w/ staircase) LR schedule with warmup Explore the dataset and runtime metrics of this model in timm model results.
DeBERTa improves the BERT and RoBERTa models using disentangled attention and enhanced mask decoder. With those two improvements, DeBERTa out perform RoBERTa on a majority of NLU tasks with 80GB training data. In DeBERTa V3, we further improved the efficiency of DeBERTa using ELECTRA-Style pre-training with Gradient Disentangled Embedding Sharing. Compared to DeBERTa, our V3 version significantly improves the model performance on downstream tasks. You can find more technique details about the new model from our paper. Please check the official repository for more implementation details and updates. The DeBERTa V3 small model comes with 6 layers and a hidden size of 768. It has 44M backbone…
Gemma is a family of open models built by Google DeepMind. Gemma 4 models are multimodal, handling text and image input (with audio supported on E2B, E4B, and 12B) and generating text output. This release includes open-weights models in both pre-trained and instruction-tuned variants. Gemma 4 features a context window of up to 256K tokens and maintains multilingual support in over 140 languages. Featuring both Dense and Mixture-of-Experts (MoE) architectures, Gemma 4 is well-suited for tasks like text generation, coding, and reasoning. The models are available in five distinct sizes: E2B, E4B, 12B, 26B A4B, and 31B. Their diverse sizes make them deployable in environments ranging from…
A Gemini 2.5 Flash Level MLLM for Vision, Speech, and Full-Duplex Mulitmodal Live Streaming on | CaseBook(Audio, Omni Full-Duplex) MiniCPM-o 4.5 is the latest and most capable model in the MiniCPM-o series. The model is built in an end-to-end fashion based on SigLip2, Whisper-medium, CosyVoice2, and Qwen3-8B with a total of 9B parameters. It exhibits a significant performance improvement, and introduces new features for full-duplex multimodal live streaming. Notable features of MiniCPM-o 4.5 include: - Leading Visual Capability. MiniCPM-o 4.5 achieves an average score of 77.6 on OpenCompass, a comprehensive evaluation of 8 popular benchmarks. With only 9B parameters, it surpasses widely…
Model · Audio classification
ast-finetuned-audioset-10-10-0.4593
Audio Spectrogram Transformer (AST) model fine-tuned on AudioSet. It was introduced in the paper AST: Audio Spectrogram Transformer by Gong et al. and first released in this repository. Disclaimer: The team releasing Audio Spectrogram Transformer did not write a model card for this model so this model card has been written by the Hugging Face team. The Audio Spectrogram Transformer is equivalent to ViT, but applied on audio. Audio is first turned into an image (as a spectrogram), after which a Vision Transformer is applied. The model gets state-of-the-art results on several audio classification benchmarks. You can use the raw model for classifying audio into one of the AudioSet classes. See…
This is the model card for the EMNLP 2021 paper WikiNEuRal: Combined Neural and Knowledge-based Silver Data Creation for Multilingual NER. We fine-tuned a multilingual language model (mBERT) for 3 epochs on our WikiNEuRal dataset for Named Entity Recognition (NER). The resulting multilingual NER model supports the 9 languages covered by WikiNEuRal (de, en, es, fr, it, nl, pl, pt, ru), and it was trained on all 9 languages jointly. If you use the model, please reference this work in your paper: The original repository for the paper can be found at https://github.com/Babelscape/wikineural. You can use this model with Transformers pipeline for NER. This model is trained on WikiNEuRal, a…
gte-Qwen2-1.5B-instruct is the latest model in the gte (General Text Embedding) model family. The model is built on Qwen2-1.5B LLM model and use the same training data and strategies as the gte-Qwen2-7B-instruct model. The model incorporates several key advancements: - Integration of bidirectional attention mechanisms, enriching its contextual understanding. - Instruction tuning, applied solely on the query side for streamlined efficiency - Comprehensive training across a vast, multilingual text corpus spanning diverse domains and scenarios. This training leverages both weakly supervised and supervised data, ensuring the model's applicability across numerous languages and a wide array of…
Welcome to the official repository for the Z-Image（造相）project! Z-Image is a powerful and highly efficient image generation model family with 6B parameters. Currently there are four variants: - Z-Image-Turbo – A distilled version of Z-Image that matches or exceeds leading competitors with only 8 NFEs (Number of Function Evaluations). It offers sub-second inference latency on enterprise-grade H800 GPUs and fits comfortably within 16G VRAM consumer devices. It excels in photorealistic image generation, bilingual text rendering (English & Chinese), and robust instruction adherence. - Z-Image – The foundation model behind Z-Image-Turbo. Z-Image focuses on high-quality generation, rich…
NVIDIA Nemotron 3 Embed Nemotron-3-Embed-1B-BF16 is a versatile text embedding model trained by NVIDIA and optimized for retrieval and semantic similarity tasks. It provides strong multilingual and cross-lingual retrieval capabilities and is designed to serve as a foundational component in text-based Retrieval-Augmented Generation (RAG) systems. This model was evaluated across 34 languages: English, Arabic, Assamese, Bengali, Bulgarian, Chinese, Danish, Dutch, Finnish, French, German, Hindi, Hinglish, Indonesian, Italian, Japanese, Korean, Malay, Marathi, Nepali, Norwegian, Persian, Portuguese, Romanian, Russian, Spanish, Swahili, Swedish, Tamil, Telugu, Thai, Ukrainian, Urdu, Vietnamese.…
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.