Unsloth releases Mistral Le Chonk 1-bit GGUF quantization, enabling local runs of a 1T-parameter model
Original title:Mistral Le Chonk can now run locally!
AI summary
Unsloth released a Dynamic 1-bit GGUF of Mistral Le Chonk (Mistral Large 4, a 1T-parameter MoE with 52B active), which can run locally on a Mac Studio, retains 91% top-1 accuracy and is about 233GB in size (80% smaller than 1.1TB FP8). The image lists hardware requirements for each quantization tier: 1-bit requires 256-270GB of memory, the smallest UD-IQ1_S takes about 233GB of disk, and it supports text and image inputs, a 1M context and 160+ languages. The GGUF and guide are at huggingface.co/unsloth/Mistral-Large-4-1T-A52B-GGUF and unsloth.ai/docs/models/mistral-large-4.
Key Takeaways
- Unsloth released a Dynamic 1-bit GGUF of Mistral Le Chonk (Mistral Large 4,a 1T-parameter MoE with…
- 1TB FP8).
- The image lists hardware requirements for each quantization tier: 1-bit requires 256-270GB of…
- The GGUF and guide are at huggingface.
- co/unsloth/Mistral-Large-4-1T-A52B-GGUF and unsloth.
Quick Facts
- Published
- Updated
- Source
- X:Unsloth (@UnslothAI)
- Category
- Products & Apps
- AI score
- 77
原文给出在 Mac Studio 上本地运行 1T 参数模型的量化方案和硬件需求表,读者可直接照做部署。
Related entities
Source & copyright
This article is based on curated titles and AI summaries from the AIHOT public API, with attribution and links back. Original copyright remains with the original publishers and authors; this site does not mirror full texts.
How to Cite
When citing this article, keep the title, date, and permalink, and credit Orange News as the source.
Orange News: Unsloth releases Mistral Le Chonk 1-bit GGUF quantization, enabling local runs of a 1T-parameter model. October 29, 2026. https://new.nat6.net/en/news/rph54wkrnzjpvov4cv0mxqatl/