---
title: "nvidia/Qwen3.6-35B-A3B-NVFP4 running in vLLM nightly on my Nvidia GB10 is actually insane"
date: 2026-06-16
canonical: https://solmaz.io/x/2066810937198432628/
x_url: https://x.com/onusoz/status/2066810937198432628
license: CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/)
---

nvidia/Qwen3.6-35B-A3B-NVFP4 running in vLLM nightly on my Nvidia GB10 is actually insane

50 tok/s, 4 concurrent generations. total 200 tok/s. ideal for spawning subagents or working in parallel

its tool calling behavior is very good as well. I will be giving it test drive on an openclaw instance, and keep you posted

More details on NVIDIA forum: https://forums.developer.nvidia.com/t/benchmark-report-qwen3-6-35b-a3b-nvfp4-on-nvidia-dgx-spark-jetson-thor-blackwell-6000-pro/371810

*Part 1/2 of a thread; root: https://solmaz.io/x/2066810937198432628/*