Qwen3.6 35B (3B active)
on NVIDIA RTX 3060 12GB · RustingStrata · 5,290 ctx
Summary
User benchmarks Qwen3.6-35B-A3B at 90.9 tok/s decode without MTP on an RTX 3060 12 GB, with 2330 tok/s prefill on a 5290-token prompt.
Setup is RustingStrata with the Unsloth Q3_K_M GGUF (15.9 GiB, does not fit in VRAM) on a Ryzen 5 7600X with 32 GB RAM, 128 tokens generated, mean of 3 reps.
With MTP drafts decode rises to 128.4 tok/s. The post compares RustingStrata against PolyStrata and llama.cpp.