Benchmark result
coder on AMD Radeon RX 7900 XT/7900 XTX/7900 GRE/7900M — 57.5 tok/s
Measured with OpenAI-compatible manual on November 5, 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
1st fastest of 4 runs of this model on AMD Radeon RX 7900 XT/7900 XTX/7900 GRE/7900M · median 42.7 tok/s.
sort
- 157.5tok/s75.6OpenAI-compatiblethis run
- 255.2tok/s75.5OpenAI-compatible
- 330.1tok/s66.1OpenAI-compatible
- 426.5tok/s72.8OpenAI-compatible
Reproduce this run
toolOpenAI-compatible manual
modelcoder
context65,536
thinkingon
clientv0.4.98+102
Set those in OpenAI-compatible, then:
llm-benchmark benchmark --model "coder" --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.