AtomicBot-ai / atomic-llama-cpp-turboquantView on GitHub
llama.cpp fork with TurboQuant WHT-rotated KV cache & weight compression + Gemma 4 MTP and Qwen 3.6 NextN speculative decoding (+30-50% throughput).
190May 14, 2026Updated this week

Alternatives and similar repositories for atomic-llama-cpp-turboquant

Users that are interested in atomic-llama-cpp-turboquant 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?