Benchmark result
Qwen3.8-27B-GSQ-RCO-BuffedMod-IQ3_S_XL-mtp-Q6K on AMD Radeon RX 7800 XT — 42.7 tok/s
Measured with llama.cpp k8 v4 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.
How this run compares
1st fastest of 2 runs of this model on AMD Radeon RX 7800 XT · median 40.3 tok/s.
sort
- 142.7tok/s86.8llama.cpp k8 v4this run
- 237.9tok/s87.8llama.cpp k8 v4
Qwen3.8-27B-GSQ-RCO-BuffedMod-IQ3_S_XL-mtp-Q6K on other hardware
Reproduce this run
toolllama.cpp k8 v4 manual
modelQwen3.8-27B-GSQ-RCO-BuffedMod-IQ3_S_XL-mtp-Q6K
context65,536
thinkingon
clientv0.4.92+102
Set those in llama.cpp k8 v4, then:
llm-benchmark benchmark --model "Qwen3.8-27B-GSQ-RCO-BuffedMod-IQ3_S_XL-mtp-Q6K" --tool "llama.cpp k8 v4"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.