Qwen3.6 35B (3B active)
on 4× 4x Tesla K40c · llama.cpp
Summary
User reports a llama.cpp fork for legacy NVIDIA GPUs running MTP Qwen3.6-35B-A3B at Q8_0 on 4x Tesla K40c (Kepler, compute capability 3.5), reaching above 60 t/s with Windows NCCL, up from 35 t/s.
Setup is a custom llama.cpp fork with CUDA graphs and Windows NCCL integration; CUDA graphs took the run from about 35 to 55 t/s.
Prefill speeds varied between 70-100 t/s, and the user calls these preliminary results from their own system rather than universal benchmarks.