Qwen3.8 27B Cold-Fusion-GAIN-V1.1-NM-DAU-NEO-MAX-NEO
on 2× NVIDIA Tesla P40 24GB · llama.cpp · 220,160 ctx
Sep 7, 2026
Use cases
coding
Summary
User reports about 46 t/s on typical short interactive decode in use on dual P40s, up from roughly 15 t/s without speculative decoding.
Setup is MTP speculative decoding with draft-mtp and ngram-simple, draft maximum 6, Qwen reasoning medium and the F16 vision projector loaded.
A synthetic 128-token decode reached 48 t/s, long-context interactive decode runs at about 20 t/s, and prefill is 444 t/s at pp512. The model is a fine-tune of Qwen3.8 27B.