Qwen3.8 27B
on 2× NVIDIA RTX 3090 · llama.cpp · 238,000 ctx
Oct 6, 2026
Use cases
coding
Summary
User reports Qwen 3.8 27B Q8_K_XL at 48.76 t/s generation and 142.46 t/s prompt processing on dual RTX 3090s.
Setup is llama.cpp via llama-swap with MTP speculative decoding (draft-mtp, n-max 3), 238000 token context, tensor split 50,50 across two cards, batch size 4096.
The figures are from the final turn of a multi-turn agentic coding run (95 prompt tokens, 90 generated, 43473 cached); per-turn generation speeds ranged from 39.58 to 77.38 t/s across the run.