xigh / herbert-rsView on GitHub
Local LLM inference engine written from scratch in Rust — hand-written AVX-512 assembly kernels, Metal & Vulkan compute shaders. Supports Qwen3, Mistral3, ... Q4/INT8/BF16 quantization.
29Mar 18, 2026Updated 3 months ago

Alternatives and similar repositories for herbert-rs

Users that are interested in herbert-rs are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.

Sorting:

Are these results useful?