AI Models
1647 models across 200 families. Family-grouped so you can track every version of a model in one place — Claude, GPT, Gemini, Llama, Qwen, Mistral, DeepSeek, and more.
Qwen
Qwen · 127 variants
QwQ is the reasoning model of the Qwen series. Compared with conventional instruction-tuned models, QwQ, which is capable of thinking and...
GPT
OpenAI · 65 variants
The gpt-audio model is OpenAI's first generally available audio model. The new snapshot features an upgraded decoder for more natural sou...
MaziyarPanahi
DeepSeek · 47 variants
- Model creator: [deepseek-ai](https://huggingface.co/deepseek-ai) - Original model: [deepseek-ai/DeepSeek-R1-0528-Qwen3-8B](https://hugg...
Unsloth
Baidu · 39 variants
This is a GGUF quantized version of [ERNIE-Image-Turbo](https://huggingface.co/baidu/ERNIE-Image-Turbo). unsloth/ERNIE-Image-Turbo-GGUF u...
Mistral
Mistral · 27 variants
This is Mistral AI's flagship model, Mistral Large 2 (version `mistral-large-2407`). It's a proprietary weights-available model and excel...
LM Studio Community
Qwen · 25 variants
_👾 [LM Studio](https://lmstudio.ai) Community models highlights program. Highlighting new & noteworthy models by the community. Join the ...
Llama
Meta · 24 variants
Llama Guard 3 is a Llama-3.1-8B pretrained model, fine-tuned for content safety classification. Similar to previous versions, it can be u...
DeepSeek
DeepSeek · 21 variants
DeepSeek-V3 is the latest model from the DeepSeek team, building upon the instruction following and coding abilities of the previous vers...
Nemotron
NVIDIA · 20 variants
NVIDIA Nemotron 3 Ultra is an open-weights frontier-scale reasoning and chat model with 550B total parameters and 55B active MoE paramete...
TRL Testing
OpenAI · 16 variants
from transformers import AutoTokenizer, GPT2Config, GPT2LMHeadModel config = GPT2Config(n_positions=512, n_embd=32, n_layer=5, n_head=4, ...
Claude
Anthropic · 15 variants
Claude 3 Haiku is Anthropic's fastest and most compact model for near-instant responsiveness. Quick and accurate targeted performance. Se...
Farbod Tavakkoli
14 variants
**OTel-LLM-27B-IT** is a context-grounded telecom language model full-parameter fine-tuned on OTel telecommunications data. It is part of...
Gemini
Google · 13 variants
Gemini Flash 2.0 offers a significantly faster time to first token (TTFT) compared to [Gemini Flash 1.5](/google/gemini-flash-1.5), while...
Gemma
Google · 12 variants
Gemma 2 27B by Google is an open model built from the same research and technology used to create the [Gemini models](/models?q=gemini). ...
Bartowski
11 variants
Using llama.cpp release b10142 for quantization. Original model: https://huggingface.co/XYZAILab/XYZ-Aquila-mini All quants made using im...
Phi
Microsoft · 11 variants
[Microsoft Research](/microsoft) Phi-4 is designed to perform well in complex reasoning tasks and can operate efficiently in situations w...
Grok
xAI · 11 variants
Grok 3 is the latest model from xAI. It's their flagship model that excels at enterprise use cases like data extraction, coding, and text...
SmolLM
9 variants
1. [Model Summary](##model-summary) 2. [Limitations](##limitations) 3. [Training](##training) 4. [License](##license) 5. [Citation](##cit...
GLM
Zhipu · 9 variants
GLM-4.5 is our latest flagship foundation model, purpose-built for agent-based applications. It leverages a Mixture-of-Experts (MoE) arch...
LFM
Liquid AI · 7 variants
src="https://cdn-uploads.huggingface.co/production/uploads/61b8e2ba285851687028d395/2b08LKpev0DNEk6DlnWkY.png" alt="Liquid AI" style="wid...
OLMo
Allen AI · 7 variants
OLMo-2 32B Instruct is a supervised instruction-finetuned variant of the OLMo-2 32B March 2025 base model. It excels in complex reasoning...
CyanKiwi
Qwen · 7 variants
Meet Qwen3-VL — the most powerful vision-language model in the Qwen series to date. This generation delivers comprehensive upgrades acros...
MAI
Microsoft · 7 variants
Low-latency Microsoft MAI coding model variant for code generation and developer assistance workflows.
MLX Community
Meta · 6 variants
The Model [mlx-community/Llama-3.1-8B-Instruct-4bit](https://huggingface.co/mlx-community/Llama-3.1-8B-Instruct-4bit) was converted to ML...
Hermes
Nous · 6 variants
Hermes 3 is a generalist language model with many improvements over Hermes 2, including advanced agentic capabilities, much better rolepl...
ERNIE
Baidu · 5 variants
A sophisticated text-based Mixture-of-Experts (MoE) model featuring 21B total parameters with 3B activated per token, delivering exceptio...
GGML
Qwen · 5 variants
Run with https://llama.app llama serve -hf ggml-org/Qwen3.8-27B-GGUF - https://huggingface.co/Qwen/Qwen3.8-27B - add info > [!IMPORTANT] ...
Sonar
Perplexity · 5 variants
Sonar is lightweight, affordable, fast, and simple to use — now featuring citations and the ability to customize sources. It is designed ...
Nova
Amazon · 5 variants
Nova 2 Lite is a fast, cost-effective reasoning model for everyday workloads that can process text, images, and videos to generate text. ...
RedHat AI
Meta · 5 variants
- **Model Architecture:** Llama-3 - **Input:** Text - **Output:** Text - **Model Optimizations:** - **Activation quantization:** FP8 - **...
MiniMax
MiniMax · 5 variants
MiniMax-M2 is a compact, high-efficiency large language model optimized for end-to-end coding and agentic workflows. With 10 billion acti...
Granite
IBM · 5 variants
Granite-4.0-H-Micro is a 3B parameter from the Granite 4 family of models. These models are the latest in a series of models released by ...
TheBloke
Meta · 4 variants
- Model creator: [Meta Llama 2](https://huggingface.co/meta-llama) - Original model: [Llama 2 7B Chat](https://huggingface.co/meta-llama/...
Kimi
Moonshot · 4 variants
Kimi K2 Instruct is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters...
Hy Mt2
3 variants
Hy-MT2-1.8B is a compact 1.8B-parameter translation model from Tencent. It supports 33 language pairs and five Chinese dialect and minori...
Command
Cohere · 3 variants
Command A is an open-weights 111B parameter model with a 256k context window focused on delivering great performance across agentic, mult...
Nano Banana
Google · 3 variants
Gemini 2.5 Flash Image, a.k.a. "Nano Banana," is now generally available. It is a state of the art image generation model with contextual...
Ornith
3 variants
[](https://deep-reinforce.com/ornith.html) Ch...
Step
StepFun · 2 variants
Step 3.5 Flash is StepFun's most capable open-source foundation model. Built on a sparse Mixture of Experts (MoE) architecture, it select...
Mercury
2 variants
Mercury 2.5 is the fastest reasoning LLM, and the latest diffusion LLM (dLLM) from Inception. Instead of generating tokens sequentially, ...
Muse Spark Contributor
Meta · 2 variants
Muse Spark 1.2 contributor tier is a reasoning model from Meta designed for developers who want to start building at an even lower cost. ...
Gemma 4
Google · 2 variants
Google Gemma 4 12B is a mid-sized multimodal model designed to run locally on laptops while supporting advanced reasoning, agentic workfl...
Ornith Nvfp
2 variants
[](https://ornith.ai/ornith_1_5.html) Chirp C...
Breeze Tts 2.Cpp
1 variant
GGUF conversions of [BreezeBlue/Breeze-TTS-2](https://huggingface.co/BreezeBlue/Breeze-TTS-2) for [**Breeze-TTS-2.cpp**](https://github.c...
Ministral
Mistral · 1 variant
A balanced model in the Ministral 3 family, Ministral 3 8B is a powerful, efficient tiny language model with vision capabilities.
Grok Imagine Video
xAI · 1 variant
xAI's image-to-video generation model featuring sharper realism, improved physics simulation, and faster generation speeds.
Z Image Loras
1 variant
+ Always use full LoRa name with "vrtlxxxx" trigger in prompt like "Alba Baptista (vrtlalbabaptista) in a swimming pool". "Woman" or "1gi...
Zonos
1 variant
GGUF weights for [**Zyphra/ZONOS2**](https://huggingface.co/Zyphra/ZONOS2), ready to run with [**zonos2.cpp**](https://github.com/Zyphra/...
Chatterbox Flash Coreml
1 variant
Compiled Core ML export of [ResembleAI/chatterbox-flash](https://huggingface.co/ResembleAI/chatterbox-flash) for Apple runtimes. This bun...
Qwen Flash
Qwen · 1 variant
Qwen3.8 Flash is a multimodal reasoning model from Alibaba. It is suited for coding assistance, agentic workflows, visual understanding, ...
Dots.Ocr
1 variant
dots.ocr: Multilingual Document Layout Parsing in a Single Vision-Language Model [** language ...
Faster Whisper Base.En
1 variant
This repository contains the conversion of [openai/whisper-base.en](https://huggingface.co/openai/whisper-base.en) to the [CTranslate2](h...
Waiillustrioussdxl_V170
1 variant
If you want to use more my checkpoint online generation, please visit here. https://tensor.art/u/762555264535746522 WAI-NSFW-illustrious-...
Kokoro Onnx Timestamped
1 variant
Kokoro is a frontier TTS model for its size of 82 million parameters (text in/audio out). - [Usage](#usage) - [JavaScript](#javascript) -...
Qwen Genesis Final
Qwen · 1 variant
> ⚡ [https://web.tribute.tg/d/KIH](https://web.tribute.tg/d/KIH) ⚡ If you like this Genesis LLM release you can [**donate**](https://web....
MiniMax M2.7
1 variant
MiniMax-M2.7 is a next-generation large language model designed for autonomous, real-world productivity and continuous improvement. Built...
Moefussion
1 variant
The goal of this project is to improve generation of moe characters since most of other models are not good at it. \ \ __Some of the mode...
Sanotts
1 variant
***sano*** (सानो) — Nepali for **"small."** A family of tiny neural text-to-speech voices — **294k to 2.27M parameters** — that run with ...
Wav2Vec2 Large Mms Azerbaijani Common_Voice15.0
1 variant
should probably proofread and complete it, then remove this comment. --> This model is a fine-tuned version of [facebook/mms-1b-all](http...
Stable Diffusion Custom
Stability AI · 1 variant
should probably proofread and complete it, then remove this comment. --> These are Custom Diffusion adaption weights for stabilityai/stab...
Vieneu Tts Nano
1 variant
[](https://github.com/pnnbao97/VieNeu-TTS) [ on [`erenfazlioglu/turk...
DeepSeek Flash Vision
DeepSeek · 1 variant
DeepSeek V4 Flash Vision Exp is an experimental vision-enabled version of [DeepSeek V4 Flash 0731](https://openrouter.ai/deepseek/deepsee...
DeepSeek Flash
DeepSeek · 1 variant
DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the cost-efficient tier of the V4.1 family. DeepSeek reports ...
Tiel Coder Mtp
1 variant
*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 r...
Indextts
1 variant
IndexTTS-2.5 is a zero-shot text-to-speech model that clones a voice from a single reference audio clip. It supports **Chinese, English, ...
Stable Diffusion Large Controlnet Canny
Stability AI · 1 variant
This repository provides the Canny ControlNet for [Stable Diffusion 3.5 Large.](https://stability.ai/news/introducing-stable-diffusion-3-...
Qwen Nvfp
Qwen · 1 variant
Quantized version of https://huggingface.co/Qwen/Qwen3.8-27B
Stable Diffusion Large Controlnet Depth
Stability AI · 1 variant
This repository provides the Depth ControlNet for [Stable Diffusion 3.5 Large.](https://stability.ai/news/introducing-stable-diffusion-3-...
Qwen Genesis Hermes
Qwen · 1 variant
> ⚡ [https://web.tribute.tg/d/KIH](https://web.tribute.tg/d/KIH) ⚡ If you like this Genesis LLM release you can [**donate**](https://web....
Gemma 128G
Google · 1 variant
This model was obtained by quantizing the weights of [gemma-3-27b-it](https://huggingface.co/google/gemma-3-27b-it) to INT4 data type. Th...
F5Tts Algerian Darja
1 variant
The first open-source F5-TTS model fine-tuned for Algerian Arabic (Darja / الدارجة الجزائرية), trained across ~399 hours of multi-domain ...
Qwen Obliterated
Qwen · 1 variant
> Genuinely uncensored. Real answers, not safety lectures. Near-stock capability. V3 applies iterative refinement on top of V2's compleme...
Z Image
1 variant
[](https://tongyi-mai.github.io/Z-Image-blog/) [!...
Qwen Hauhaucs Aggressive Mtp
Qwen · 1 variant
> **HauhauCS FastMTP: up to 3.02x document TG and 1.93x reasoning TG versus non-MTP — plus up to 35.2% more document TG and 21.1% more re...
Cosyvoice
1 variant
GGUF conversion of [FunAudioLLM/Fun-CosyVoice3-0.5B-2512](https://huggingface.co/FunAudioLLM/Fun-CosyVoice3-0.5B-2512) for use with [Cris...
Surya Ocr
1 variant
Surya is a 650M param OCR model with these features: - Accuracy - scores 83.3% on [olmOCR-bench](https://huggingface.co/datasets/allenai/...
Netayume Lumina Image
1 variant
**I. Introduction** NetaYume Lumina is a text-to-image model fine-tuned from [Neta Lumina](https://huggingface.co/neta-art/Neta-Lumina), ...
Schematron Small
1 variant
Schematron V2 Small is a 3B-parameter HTML-to-JSON extraction model from Inference.net. It prioritizes extraction quality for complex sch...
Soprano
1 variant
[](https://github.com/ekwek1/soprano) [ created with abliteration (see [remove-refus...
Pony Diffusion Xl
1 variant
GGUF conversions of [Pony Diffusion V6 XL](https://huggingface.co/AstraliteHeart/pony-diffusion-v6) for **on-device** image generation wi...
Gemma
Google · 1 variant
A 26B MoE model (3.8B active params) that generates 256 tokens in parallel via discrete diffusion, delivering up to 4x speedup over autor...
GLM Flash
1 variant
This model always redirects to the latest model in the GLM Flash family.
GLM Imat
Zhipu · 1 variant
_Llama.cpp imatrix quantization of THUDM/glm-4-9b-chat_ Original Model: [THUDM/glm-4-9b-chat](https://huggingface.co/THUDM/glm-4-9b-chat)...
Ideogram
1 variant
Quantized GGUF diffusion transformer weights for [Ideogram 4](https://huggingface.co/ideogram-ai/ideogram-4-fp8), converted from the orig...
Claude Fable
Anthropic · 1 variant
Anthropic's most capable widely released model, built for demanding reasoning and long-horizon agentic work. Features adaptive thinking, ...
Kimi K2
Moonshot · 1 variant
Open-source coding model from Moonshot AI. Improves on K2.6 with +21.8% on Kimi Code Bench v2, +11.0% on Program Bench, and +31.5% on MLS...
MiniMax M-Series
MiniMax · 1 variant
MiniMax-M3 is an open-weight frontier model combining coding and agentic capabilities, MiniMax Sparse Attention with up to a 1M-token con...
Veena
1 variant
Veena is a state-of-the-art neural text-to-speech (TTS) model developed by Maya Research, designed for English and Indian languages. Buil...
Breeze Tts
1 variant
> [!IMPORTANT] > Source code is licensed under Apache 2.0. Breeze TTS 2 model weights, derivative models, and self-hosted outputs are for...
GPT Astra
OpenAI · 1 variant
GPT-6 Astra is OpenAI's flagship model for demanding end-to-end work. It is suited for advanced analysis, software engineering, deep rese...
Qwen Gsq Rco
Qwen · 1 variant
GSQ-RCO GGUF release card, TEMPLATE (filled with Qwen3.8-27B as the example). To publish a new model, copy this folder and change only: 1...
Vibevoice
1 variant
GGUF conversion of [vibevoice/VibeVoice-7B](https://huggingface.co/vibevoice/VibeVoice-7B) for [audio.cpp](https://github.com/0xShug0/aud...
Orpheus Tts Multilingual
1 variant
A multilingual, multi-speaker text-to-speech model fine-tuned from [`unsloth/orpheus-3b-0.1-pretrained`](https://huggingface.co/unsloth/o...
LongCat-Video
1 variant
Open-source audio-driven avatar video generation model built on LongCat-Video. It supports audio-text-to-video, audio-image-text-to-video...
Vieneu Tts Turbo
1 variant
This repository contains the official GGUF quantized model package for **VieNeu-TTS v3 Turbo (48 kHz)**, fully integrated and supported n...
Kokoro Inno Clone Tuner
1 variant
pip install inno-kokoro Zero-shot voice tuner for [Kokoro-82M](https://huggingface.co/hexgrad/Kokoro-82M). Intended as an exploration and...
Union Alpha
1 variant
Union Alpha is a multimodal model built for research, coding, and agentic workflows, while delivering frontier-level performance across a...
GPT Astra
OpenAI · 1 variant
This model always redirects to the latest model in the OpenAI GPT Astra family.
GPT Sol
OpenAI · 1 variant
This model always redirects to the latest model in the OpenAI GPT Sol family.
GPT Terra
OpenAI · 1 variant
This model always redirects to the latest model in the OpenAI GPT Terra family.
Whisper Large Turbo German
1 variant
This model map provides information about a model based on Whisper Large v3 that has been fine-tuned for speech recognition in German. Wh...
Tiny Random Z Image
1 variant
Ternary Bonsai
1 variant
Bonsai 2 27B is a 27B-parameter reasoning model from PrismML derived from Qwen3.8-27B. It supports coding, mathematics, tool calling, and...
Echo Tts
1 variant
GGUF files released for the audio.cpp echo_tts model. Includes the s1 codec weights. f16 and q8_0 This work is not affiliated or endorsed...
Vibevoice
1 variant
VibeVoice is a novel framework designed for generating expressive, long-form, multi-speaker conversational audio, such as podcasts, from ...
GPT Luna
OpenAI · 1 variant
This model always redirects to the latest model in the OpenAI GPT Luna family.
GLM
1 variant
This model always redirects to the latest GLM model from Z.ai.
Hy4
1 variant
Tencent: Hy4 preview is a mixture-of-experts model from Tencent, with 49B active parameters out of 770B total. It is designed for coding ...
Jirackultra_14B
1 variant
A fast and efficient 14B model optimized for CPU inference. The model was refactored with BitNet features and an updated tokenizer that i...
Indic Conformer Multilingual
1 variant
Aion
1 variant
Aion 3.5 is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models. It uses a collaborative g...
Aion Mini
1 variant
Aion 3.5 Mini is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models. It is the smaller, l...
Jirackultra_1B
1 variant
A fast and efficient ~1.5B model optimized for CPU inference. The model was refactored with BitNet features and an updated tokenizer that...
Audio Tts
1 variant
**The smallest zero-shot TTS worth running.** [. **Original model:** [ekwek1/soprano](https://gith...
Dots.Mocr
1 variant
dots.mocr [](https://huggingface.co/rednote-...
Flux.2 Klein Mflux
1 variant
4-bit quantized weights of [FLUX.2 [klein] 4B](https://huggingface.co/black-forest-labs/FLUX.2-klein-4B) by Black Forest Labs, optimized ...
Qwen Image
Qwen · 1 variant
🤖 ModelScope | 🤗 HuggingFace | 📑 Blog | 🖥️ Demo | 🫨 Discord | 💬 WeChat We are excited to open-source **Qwen-Image-2.1**, a...
Ember
1 variant
Ember-1 is a specialized reasoning model from Fireworks Research, built on [Kimi K3](https://openrouter.ai/moonshotai/kimi-k3). It is des...
Qwen Image Viggle Turbo
Qwen · 1 variant
**Built with Qwen.** A few-step distilled student of [Qwen/Qwen-Image-2.1](https://huggingface.co/Qwen/Qwen-Image-2.1), trained by Viggle...
Qwen Nvfp Rtx
Qwen · 1 variant
Runs on **SparkInfer, SGLang and vLLM** unmodified — configs for all three are [below](#serving). Serving many users at once? See [concur...
Command A Plus
Cohere · 1 variant
Command A+ is Cohere's flagship model for enterprise agentic workflows. It accepts text and image inputs with a 192K context window, supp...
Auk And Flash
1 variant
These GGUF files are for use with [audio.cpp](https://github.com/0xShug0/audio.cpp). The card's `base_model` points to the [Tencent AuK b...
Moss Tts
1 variant
Self-contained GGUF packages of [OpenMOSS-Team/MOSS-TTS-v1.5](https://huggingface.co/OpenMOSS-Team/MOSS-TTS-v1.5), for [audio.cpp](https:...
Ling Flash Vl
1 variant
Ling 3.0 Flash VL builds on Ling 3.0 Flash (124B total / 5.5B active MoE from InclusionAI), further strengthening its language capabiliti...
DeepSeek Flash
DeepSeek · 1 variant
This model always redirects to the latest model in the DeepSeek Flash family.
DeepSeek Pro
DeepSeek · 1 variant
This model always redirects to the latest model in the DeepSeek Pro family.
Qwen Image
Qwen · 1 variant
> [!IMPORTANT] > The uncensored GGUFs are now available! > If you encounter any issues or would like to share your generated images, feel...
Claude Opus
Anthropic · 1 variant
Claude Opus 5.5 is Anthropic's flagship model for demanding reasoning, coding, and long-horizon agentic work, succeeding Claude Opus 5. I...
Gemini Nano
Google · 1 variant
Gemini Nano is Google's most efficient Gemini model, built to run directly on-device on Android through AICore and the ML Kit GenAI APIs....
Gemini Flash
Google · 1 variant
Gemini 3.8 Flash is Google's most intelligent Flash model with significant gains from 3.7 Flash across software engineering, agentic task...
Fugu Max
1 variant
Fugu Max is the cost-performance model in Sakana AI's Fugu family. Rather than a single monolithic model, Fugu is a learned multi-agent o...
Pareto
1 variant
Pareto is a multimodal composite model built for research, coding, and agentic workflows, while delivering frontier-level performance acr...
Maya
1 variant
**Maya-1** is a state-of-the-art speech model for expressive voice generation, designed to capture human emotion and enable precise voice...
Fugu Ultra
1 variant
Fugu Ultra v2 is the higher-performance model in Sakana AI's Fugu family. Rather than a single monolithic model, Fugu is a learned multi-...
Ling Flash Fin
1 variant
Ling 3.0 Flash Fin is a finance-focused mixture-of-experts model from InclusionAI, built on Ling 3.0 Flash with 5.1B active parameters ou...
Qwen Nvfp
NVIDIA · 1 variant
The NVIDIA Qwen3.5-122B-A10B-NVFP4 model is the quantized version of Alibaba's Qwen3.5-122B-A10B model, which is an auto-regressive langu...
Huihui Qwen Abliterated Mtp
Qwen · 1 variant
This is an uncensored version of [Qwen/Qwen3.6-27B](https://huggingface.co/Qwen/Qwen3.6-27B) created with abliteration (see [remove-refus...
Nex N2.5 Pro
1 variant
Nex-N2.5 is an agentic model built to turn goals into working, verified outcomes. Its core strength is agentic coding within a visual fee...
Qwen Image
Qwen · 1 variant
The license of the quantized files follows the license of the original model: - Qwen RESEARCH LICENSE AGREEMENT: https://huggingface.co/Q...
GLM
Zhipu · 1 variant
GLM-5.2 is ZhipuAI's latest open-weights frontier model with major gains in coding, agentic tasks, and long-horizon reasoning. Ships two ...
Qwen Heretic Abliterated
Qwen · 1 variant
**RVN** is a double-refined abliterated variant of **Qwen3.8-27B**, built on top of [`trohrbaugh/Qwen3.8-27B-heretic-ara`](https://huggin...
Qwythos
1 variant
GGUF quantizations of **[empero-ai/Qwythos-9B-v2](https://huggingface.co/empero-ai/Qwythos-9B-v2)** for [llama.cpp](https://github.com/gg...
Gemma Qat Hauhaucs Balanced
Google · 1 variant
> **[Join the Discord](https://discord.gg/SZ5vacTXYf)** for updates, roadmaps, projects, or just to chat. Gemma4-12B (QAT) uncensored by ...
Qwen Max Prime
Qwen · 1 variant
Qwen3.8 Max Prime is a higher-throughput variant of Qwen3.8 Max from Alibaba's Qwen team, served as a separate SKU at a higher price poin...
Space Bunny Alpha
1 variant
Space Bunny Alpha is an anonymous large model with blazing-fast inference, strong coding capabilities and native multimodal input support...
Solar Mini
1 variant
Solar Mini 4 is Upstage's compact, cost-efficient language model, a 35B-parameter mixture-of-experts with 3B active parameters and a 524K...
Ljspeech Jets Onnx
1 variant
[imdanboy/jets](https://huggingface.co/imdanboy/ljspeech_tts_train_jets_raw_phn_tacotron_g2p_en_no_space_train.total_count.ave) exported ...
Qwen Omni Flash
Qwen · 1 variant
Qwen3.8 Omni Flash is an omni-modal reasoning model from Alibaba, the first Qwen model built around agentic capabilities with native audi...
GPT Astra Pro
OpenAI · 1 variant
GPT-6 Astra Pro is the same underlying model as [GPT-6 Astra](https://openrouter.ai/openai/gpt-6-astra), served with `reasoning.mode` set...
Vllm Translategemma
Google · 1 variant
This is a modified version of [google/translategemma-4b-it](https://huggingface.co/google/translategemma-4b-it) optimized for deployment ...
GPT Luna
OpenAI · 1 variant
GPT-6 Luna is the fast, cost-efficient model in OpenAI's GPT-6 series, positioned below GPT-6 Sol. It is suited for high-volume and laten...
GLM Prime
1 variant
GLM-5.3-Prime is the high-speed variant of Z.ai's GLM-5.3, inheriting its full capabilities while delivering 1.5–2× the output throughput...
Mimo Pro
1 variant
MiMo-V2.6-Pro is the flagship foundation model developed by Xiaomi. Built at a scale of over 1T parameters, it is designed to push the ce...
Audio Tts
1 variant
GGUF conversion of **[Audio8/Audio8-TTS-Preview-0.6b](https://huggingface.co/Audio8/Audio8-TTS-Preview-0.6b)** for [audio.cpp](https://gi...
Mimo Pro Ultraspeed
1 variant
MiMo-V2.6-Pro-UltraSpeed is the fast speed edition of Xiaomi's flagship foundation model, MiMo-V2.6-Pro. Built from the same 1T MiMo-V2.6...
Mimo Flash
1 variant
MiMo-V2.6-Flash is an open-source foundation model developed by Xiaomi. Built on a Mixture-of-Experts architecture with 309B total parame...
GPT Luna Pro
OpenAI · 1 variant
GPT-6 Luna Pro is the same underlying model as [GPT-6 Luna](https://openrouter.ai/openai/gpt-6-luna), served with `reasoning.mode` set to...
GPT Sol
OpenAI · 1 variant
GPT-6 Sol is the cost-efficient high-end model in OpenAI's GPT-6 series, positioned below the flagship GPT-6 Astra and above the fast GPT...
GPT Sol Pro
OpenAI · 1 variant
GPT-6 Sol Pro is the same underlying model as [GPT-6 Sol](https://openrouter.ai/openai/gpt-6-sol), served with `reasoning.mode` set to `p...
GLM
1 variant
GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks. It supports text...
GLM Flash
1 variant
GLM-5.3-Flash is a native multimodal model from Z.ai. It is suited for efficient coding and long-horizon agent tasks. Its hybrid sparse a...
Perceptron Mk1.5
1 variant
Perceptron Mk1.5 is Perceptron's embodied reasoning model for physical agents. It accepts text, image, video, and audio input, and answer...
Unlimited Ocr
1 variant
AWQ 4-bit (W4A16) quantization of [**baidu/Unlimited-OCR**](https://huggingface.co/baidu/Unlimited-OCR), a 3B vision-language OCR model t...
Jev Router
1 variant
Jev Router picks the best model and reasoning effort for each request, balancing quality, speed, and cost. It runs on [Jev](https://openr...
Qwen The Defiant Fable Heretic Neo Imatrix Max Mtp
Qwen · 1 variant
and it does so in 4bit and 8bit. Regular and MTP (fast) NEO IMATRIX GGUFs provided. (this model is part of the Qwen 3.6 27B Fable Fusion ...
Qwen Turbo Fable Cold Fusion Heretic Neo Coder Max Mtp
Qwen · 1 variant
in 8 bit and over 718 arc-c in 4 bit. This version is called TURBO because it drastically reduces thinking tokens (by 1/2 to as high as 1...
Voxcpm
1 variant
GGUF-converted weights of [openbmb/VoxCPM2](https://huggingface.co/openbmb/VoxCPM2) for the C++/ggml inference engine [llama.cpp-omni](ht...
Kartoffel_Orpheus 3B_German_Natural
1 variant
Qwen Dapo
Qwen · 1 variant
Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (M...
Magenta RealTime
Google · 1 variant
Open-weights live music generation model from Google DeepMind for low-latency, on-device streaming music generation controlled by text pr...
Qwen
Qwen · 1 variant
Uncensored [Qwen3.8-27B](https://huggingface.co/Qwen/Qwen3.8-27B), published as GGUF quantizations with the multi token prediction (MTP) ...
Nex N2.5 Mini
1 variant
Nex-N2.5 is an agentic model built to turn goals into working, verified outcomes. Its core strength is agentic coding within a visual fee...
Sopro Turbo
1 variant
[](https://research.haloneuro.ai/posts/sopro-v2) [![...
Rax
1 variant
> [!Note] > This repository contains model weights and configuration files for the post-trained model in the Hugging Face Transformers fo...
Hubert Large Ls960 Ft
Meta · 1 variant
[Facebook's Hubert](https://ai.facebook.com/blog/hubert-self-supervised-representation-learning-for-speech-recognition-generation-and-com...
DeepSeek Flash Dspark
DeepSeek · 1 variant
**Note: DeepSeek-V4-Flash-DSpark** is **not** a new model. It is the same checkpoint with an additional speculative decoding module attac...
Girlslike Zimage
1 variant
用于**测试**基于 Z-Image Base/Turbo BF16 训练的人物 LoKR / LoRA，仅代表个人审美与训练效果。实际生成结果仅供测试，**请勿用于**冒充、欺骗或其他不当用途。 后缀为**zi**代表基于z-image base训练，**zit**则代表...
Wav2Vec2 Large Xlsr Japanese Hiragana
1 variant
Fine-tuned [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on Japanese using the [Common Voice]...
Qwen Asr
Qwen · 1 variant
The Qwen3-ASR family includes **Qwen3-ASR-1.7B** and **Qwen3-ASR-0.6B**, which support language identification and ASR for 52 languages a...
Qwen Text Nvfp Mtp
Qwen · 1 variant
NVFP4-quantized text-only sibling of [`Qwen/Qwen3.6-27B`](https://huggingface.co/Qwen/Qwen3.6-27B), with the **MTP (Multi-Token Predictio...
Kokoro Ru
1 variant
Russian text-to-speech at **82M parameters**, running **9.8x faster than realtime on a laptop CPU** with no GPU. Three fixed voices from ...
Anima
1 variant
Join my discord server!: https://discord.gg/em4PjwZvWx If you'd like to support me or to support the training progress: [![Ko-fi](https:/...
Krea2_Turbo_Diff_Loras
1 variant
These LoRAs were extracted from fine-tuned checkpoints. I did this primarily for myself because LoRAs are easier to work with: they can b...
Audio.Cpp Fork
1 variant
This directory contains audio.cpp-native GGUF conversions of multiple speech models. These files are intended for use with [audio.cpp](ht...
Claude Fable
Anthropic · 1 variant
Claude Fable 5.1 improves on Claude Fable 5 across the board, with the biggest gains in agentic coding, long-running agentic workflows, a...
Mistral Large
Mistral · 1 variant
Mistral Large 3 2512 is Mistral’s most capable model to date, featuring a sparse mixture-of-experts architecture with 41B active paramete...
Mistral Small
Mistral · 1 variant
Mistral Small 4 is the next major release in the Mistral Small family, unifying the capabilities of several flagship Mistral models into ...