Indras-Mirror / llama.cpp-turboq-mtpView on GitHub
Fused TBQ4 Flash Attention + MTP + Shared Tensors + Qwen35 SWA Hybrid for llama.cpp — 82+ tok/s, lossless 4.25 bpv KV cache, SWA-bounded deep-context decode (w/ long-range recall) on RTX 4090
92Aug 26, 2026Updated this week

Alternatives and similar repositories for llama.cpp-turboq-mtp

Users that are interested in llama.cpp-turboq-mtp 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?