Qwen3.8 27B
on NVIDIA RTX 4070 · llama.cpp · 32,768 ctx
Sep 7, 2026
Summary
User reports 12.55 t/s for a 256 token response and 11.65 t/s for a 512 token response on an RPC split across an RTX 4070 Ti and an M5 MacBook Air with 16 GB unified memory.
MTP off gives 9.72 t/s.
The use case is agentic coding.