The Local LLM Index / Quantization & Formats / #118
sudoingX/qwen38-mtp
by sudoingX · Quantization & Formats · updated 1mo ago
One llama.cpp flag unlocks +33-39% decode speed for Qwen3.8-27B on consumer GPUs. The MTP head already ships inside your GGUF. Recipe, paired benchmarks, probe tool.
60
momentum
364
stars
101
forks
#118
rank