Qwen3.6 10.5B Math-Physics

User releases Math-Physics-Qwen3.6-10.5B, a 10.5B specialist distilled from Qwen3.6-35B-A3B by expert pruning, reporting ~128-138 tok/s single-stream decode at Q4_K_M and ~87-100 tok/s at Q8_0 on an RTX 5060 Ti. Setup is llama.cpp with Q4_K_M weights, q8_0 KV cache and 8192 context; the Q4 file is ~6.5 GB and the Q8 ~11.2 GB, fitting within 16GB VRAM. Aggregated throughput exceeds 300 tok/s across 8 concurrent slots (-np 8). Screening scores on Q8_0: MATH-500 levels 4-5 80.0%, GPQA-Diamond physics 80.0%, MMLU-Pro physics 63.3%, UGPhysics 36.7%.