Qwen3.5 35B (3B active)
on NVIDIA RTX Pro 6000 Blackwell · llama.cpp · 2,048 ctx
Summary
User benchmarks a GDN chunked kernel pull request in llama.cpp, reporting prompt-processing throughput on several GPUs and models.
On an RTX PRO 6000 Blackwell with Qwen3.5-35B-A3B-Q8_0 at 2048 prompt tokens, the PR reaches 16459.56 tok/s against 13653.58 tok/s on master, a 20.6% gain.
The table also covers RTX 5090, RTX 4090, RTX 3090 and Spark GB10 across Qwen3.5-35B-A3B, Qwen3.6-35B-A3B, Qwen3.8-27B and Qwen3.8-Flash-Next at 2048 and 4096 prompt tokens.