Benchmark result
ISTA-DASLab/Qwen3.8-27B-GSQ-RCO-GGUF:IQ3_S-mtp on Advanced Micro Devices, Inc. [AMD/ATI] Device 7551 — 32.2 tok/s
Measured with llama.cpp b11146-7fe450e19 on October 8, 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
ISTA-DASLab/Qwen3.8-27B-GSQ-RCO-GGUF:IQ3_S-mtp on other hardware
Reproduce this run
toolllama.cpp b11146-7fe450e19
modelISTA-DASLab/Qwen3.8-27B-GSQ-RCO-GGUF:IQ3_S-mtp
context65,536
thinkingon
effortmedium
samplingtemperature 1 · top_p 0.949999988079071 · top_k 20 · min_p 0 · presence_penalty 0 · repeat_penalty 1
clientv0.4.85+101
Set those in llama.cpp, then:
llm-benchmark benchmark --model "ISTA-DASLab/Qwen3.8-27B-GSQ-RCO-GGUF:IQ3_S-mtp" --tool "llama.cpp"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.