transformers now loads GGUF quantized models directly, with local inference performance close to llama.cpp
Original title:Transformers now runs llama.cpp quants
AI summary
Hugging Face announced that transformers can now run GGUF quantized models directly, loading GGUF checkpoints from the Hub by passing gguf_file to from_pretrained and reusing ggml's Metal kernels.
Quick Facts
- Published
- Updated
- Source
- Hugging Face 社区博客(混合发现)
- Category
- Products & Apps
- AI score
- 73
官方宣布 transformers 直接加载 GGUF,给出在 Apple Silicon 上接近 llama.cpp 的实测吞吐和加载方法,可帮助本地推理用户选择工作流。
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: transformers now loads GGUF quantized models directly, with local inference performance close to llama.cpp. September 22, 2026. https://new.nat6.net/en/news/cmuckj3gv09kiroed6m91iyre/