Benchmark result
strata_iq3s_256k on AMD Radeon RX 7900 XTX — 39.8 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
2nd fastest of 2 runs of this model on AMD Radeon RX 7900 XTX · median 40.0 tok/s.
sort
- 140.2tok/s86.1OpenAI-compatible
- 239.8tok/s86.8OpenAI-compatiblethis run
Reproduce this run
toolOpenAI-compatible manual
modelstrata_iq3s_256k
context32,768
thinkingon
clientv0.4.98+102
Set those in OpenAI-compatible, then:
llm-benchmark benchmark --model "strata_iq3s_256k" --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.