carlosfundora / llama.cpp-1-bit-turboView on GitHub
HIP/ROCm fork optimized for AMD RDNA2 (gfx1030) with PrismML Q1_0_G128 1-bit quant support, RotorQuant, TurboQuant, EAGLE3 and P-EAGLE speculative decoding, and full Wave32 kernel optimizations.
19Jun 23, 2026Updated 3 weeks ago

Alternatives and similar repositories for llama.cpp-1-bit-turbo

Users that are interested in llama.cpp-1-bit-turbo 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?