Qwen3.8 27B

User reports Qwen3.8 27B at 50-60 t/s generation and 350 t/s prefill on 2x Tesla P100 16GB with a custom llama.cpp fork. Setup is llama.cpp with Q6_K quant, 262144 context, batch 32768, ubatch 1024, and MTP speculative decoding. At 260k context, generation is 30-35 t/s and prefill is 110 t/s. GPUs are capped at 175W/250W each and run at 79C with minor thermal throttling; user estimates 5-10% higher numbers with better cooling.