







Image-Text-to-Text model with 177B parameters. Download, explore files and run it on Hugging Face.
s-zaizen/DeepSeek-V4.1-Flash-Abliterated · Hugging Face
Image-Text-to-Text model with 763B parameters. Download, explore files and run it on Hugging Face.
qwen3.5:27b
Qwen 3.5 is a family of open-source multimodal models that delivers exceptional utility and performance.

Georgi Gerganov on Twitter / X
HuggingFace just shipped in-browser GGUF editingIt allows you to edit GGUF metadata in the comfort of your browser, without having to even download the full model. This feature is enabled via the Xet technology that makes partial file updates possible. pic.twitter.com/uKqsvfLHcT— Georgi Gerganov (@ggerganov) October 7, 2025
Ava - a Hugging Face Space by townbox
Talk face to face with LFM3-Omni, running in your browser
Qwen (Qwen)
Org profile for Qwen on Hugging Face, the AI community building the future.
Niko1221/Strata
Qwen3.8-Flash-Next on any consumer hardware: one-click install for Windows / Linux. Strata inference engine, OpenAI/Anthropic API on localhost, optional image input.
Qwen3.8-Flash-Next: How to Run Locally | Unsloth Documentation
Guide to run Qwen3.8-Flash-Next locally.

Apple stumbled into succes with MLX
201 votes, 76 comments. Qwen3-next 80b-a3b is out in mlx on hugging face, MLX already supports it. Open source contributors got this done within 2…
Qwen3-Coder: Agentic Coding in the World
GITHUB HUGGING FACE MODELSCOPE DISCORD Today, we’re announcing Qwen3-Coder, our most agentic code model to date. Qwen3-Coder is available in multiple sizes, but we’re excited to introduce its most powerful variant first: Qwen3-Coder-480B-A35B-Instruct — a 480B-parameter Mixture-of-Experts model with 35B active parameters which supports the context length of 256K tokens natively and 1M tokens with extrapolation methods, offering exceptional performance in both coding and agentic tasks. Qwen3-Coder-480B-A35B-Instruct sets new state-of-the-art results among open models on Agentic Coding, Agentic Browser-Use, and Agentic Tool-Use, comparable to Claude Sonnet 4.
DeepSeek-V4.1-Flash: Run Locally Guide | Unsloth Documentation
Run DeepSeek-V4.1-Flash-1017 locally with Unsloth GGUFs and Engram n-gram offloading.

ONNX Model Explorer - a Hugging Face Space by onnx-community
This tool lets you upload an ONNX model file and instantly see a clear, interactive diagram of its structure, including layers, inputs, and outputs. You can navigate through the graph to understand...
Release Auto compaction (preview) + LAN Remote Access · unslothai/unsloth
Thanks for the support for Qwen3.8-27B and Unsloth Desktop last week! For this release, we merged 200+ PRs to introduce many new features, fixes including: Auto Compaction (Experimental) for longe...
Vaibhav (VB) Srivastav on Twitter / X
Hello local LLM enjoyers, starting today you should be able to find if you can run a GGUF directly from the Hugging Face page! 🔥Super psyched to see this out in the wild - this has been a big ask from the community!P.S. It'll pick all the hardwares you've defined under your… pic.twitter.com/7PTFCUHftl— Vaibhav (VB) Srivastav (@reach_vb) April 1, 2025
To The Qwen Team, Kindly Contribute to Qwen3-Next GGUF Support!
442 votes, 126 comments. If you haven't noticed already, Qwen3-Next hasn't yet been supported in llama.cpp, and that's because it comes with a custom…
DALL·E 3
This page introduced DALL·E 3, OpenAI’s 2023 image generation system with stronger prompt adherence and ChatGPT integration. Explore ChatGPT Images 2.5.
