Qwen3.6 27B
on NVIDIA RTX 3090 · llama.cpp · 200,000 ctx
Sep 24, 2026
Summary
User reports Qwen3.6 27B at 50.27 t/s narrative and 58.92 t/s code on a single RTX 3090 at 200K context.
Setup is llama.cpp with MTP speculative decoding and the Unsloth Q4_K_M GGUF; prefill measured 1025 t/s.
Soak testing gave a p50 of 54.5 t/s with 102 percent retention, and a verify-stress ladder showed 183K fill capacity with margin.