Benchmark result
Qwen3.8-27B-GSQ-RCO-IQ3_S-mtp-ASCII-Condensed on AMD Radeon RX 9070/9070 XT/9070 GRE — 39.2 tok/s
Measured with OpenAI-compatible manual on October 27, 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 3 runs of this model on AMD Radeon RX 9070/9070 XT/9070 GRE · median 39.2 tok/s.
sort
- 140.0tok/s72.3OpenAI-compatible
- 239.2tok/s89.1OpenAI-compatiblethis run
- 339.1tok/s88.4OpenAI-compatible
Qwen3.8-27B-GSQ-RCO-IQ3_S-mtp-ASCII-Condensed on other hardware
Reproduce this run
toolOpenAI-compatible manual
modelQwen3.8-27B-GSQ-RCO-IQ3_S-mtp-ASCII-Condensed
context131,072
clientv0.4.98+102
Set those in OpenAI-compatible, then:
llm-benchmark benchmark --model "Qwen3.8-27B-GSQ-RCO-IQ3_S-mtp-ASCII-Condensed" --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.