Qwen3.8 27B
on 2× NVIDIA RTX 3090 · vLLM · 262,144 ctx
Sep 7, 2026
Use cases
codingagentic
Summary
User reports DFlash2 speculative decoding with LMCache KV offload, with decode speeds varying by task: code 268 t/s, agent 165 t/s, mixed 97 t/s, prose 76 t/s.
Prefill runs at 15-17k t/s, and the KV cache pool holds 18M tokens on NVMe L2.
The setup required patches to avoid corruption.