Benchmark result
text-model on NVIDIA RTX A2000 12GB +1 more — 72.0 tok/s
Measured with OpenAI-compatible manual on October 13, 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 NVIDIA RTX A2000 12GB +1 more · Multi-GPU · median 92.0 tok/s.
sort
- 195.4tok/s81.0OpenAI-compatible
- 292.0tok/s72.2OpenAI-compatible
- 372.0tok/s69.3OpenAI-compatiblethis run
Reproduce this run
toolOpenAI-compatible manual
modeltext-model
context65,536
thinkingon
clientv0.4.92+102
Set those in OpenAI-compatible, then:
llm-benchmark benchmark --model "text-model" --tool "OpenAI-compatible"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.