Benchmark result
Huihui-Qwen3.8-27B-abliterated-Swift-1.5-GSQ-RCO-IQ3_S-mtp on AMD Radeon RX 7800 XT — 51.5 tok/s
Measured with rdna-fast-huihui-think manual on November 16, 2026.
Support llm-bench.io
llm-bench.io is free. If it helped you, I'd appreciate your support to cover the infrastructure costs.
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 4 runs of this model on AMD Radeon RX 7800 XT · median 49.0 tok/s.
sort
- 153.5tok/s60.4rdna-fast-huihui
- 251.5tok/s68.6rdna-fast-huihui-thinkthis run
- 346.5tok/s89.8llama.cpp
- 440.5tok/s88.4llama.cpp
Reproduce this run
toolrdna-fast-huihui-think manual
modelHuihui-Qwen3.8-27B-abliterated-Swift-1.5-GSQ-RCO-IQ3_S-mtp
context8,192
thinkingon
clientv0.4.99+102
Set those in rdna-fast-huihui-think, then:
llm-benchmark benchmark --model "Huihui-Qwen3.8-27B-abliterated-Swift-1.5-GSQ-RCO-IQ3_S-mtp" --tool "rdna-fast-huihui-think"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.