Qwen3.8 27B
on NVIDIA RTX 5090 · llama.cpp · 262,144 ctx
Sep 7, 2026
Summary
User reports a DFlash2 draft model with a Q4_K_M quant, giving roughly 2x decode speedup with 5 draft tokens and roughly 2.7x with 7 draft tokens.
Setup is a 4-bit Unsloth model at 256k context, with draft acceptance identical to Q8_0.
Prefill slows by roughly 15% with the draft model.