Qwen3.6 35B (3B active)

Sep 3, 2026

Throughput

237.9 tokens/s prompt processing (prefill)Prompt processing measures input prefill speed; it does not tell you the time to first token.

Quant

UD-Q8_K_XL (GGUF)

System RAM

128 GB

Summary

User reports Qwen3.6 35B A3B prompt processing at 237.9 t/s at depth 0 on Strix Halo 128GB.