Benchmark result
a3-qwen3.5-9b on 2× NVIDIA A10G — 112.2 tok/s
Measured with ninfer manual on November 4, 2026.
What the model built
Open full screen →The coding scenario asks for a playable game in a single HTML file. This is exactly what the model returned, unedited; the frame only adds a line that tells this page how tall it is.
How this run compares
3rd fastest of 3 runs of this model on 2× NVIDIA A10G · Multi-GPU · median 112.9 tok/s.
sort
- 1119.4tok/s73.5ninfer
- 2112.9tok/s63.1ninfer
- 3112.2tok/s61.9ninferthis run
Reproduce this run
toolninfer manual
modela3-qwen3.5-9b
context65,536
thinkingoff
clientv0.4.98+102
Set those in ninfer, then:
llm-benchmark benchmark --model "a3-qwen3.5-9b" --tool "ninfer"The client prompts for context length and thinking mode, and for the KV cache dtype on Unsloth Studio. Sampling is left at the model default — the values above are what the tool reported using, not overrides the client sent.