Benchmark result
MiMo-V2.6-Distill-Qwen-9B-Q8_0 on AMD Radeon RX 7800 XT — 51.8 tok/s
Measured with OpenAI-compatible manual on October 18, 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.
Reproduce this run
toolOpenAI-compatible manual
modelMiMo-V2.6-Distill-Qwen-9B-Q8_0 (Q8_0)
context200,000
thinkingon
clientv0.4.92+102
Set those in OpenAI-compatible, then:
llm-benchmark benchmark --model "MiMo-V2.6-Distill-Qwen-9B-Q8_0" --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.