Benchmark result
unsloth/Qwen3.8-27B-GGUF:UD-Q4_K_M on AMD Radeon AI PRO R9700 — 55.6 tok/s
Measured with llama.cpp b11669-620d2225c on October 28, 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
unsloth/Qwen3.8-27B-GGUF:UD-Q4_K_M on other hardware
Reproduce this run
toolllama.cpp b11669-620d2225c
modelunsloth/Qwen3.8-27B-GGUF:UD-Q4_K_M (Q4_K_M)
context65,536
effortxhigh (model default)
think limitnone
samplingtemperature 1 · top_p 0.949999988079071 · top_k 20 · min_p 0 · presence_penalty 1.5 · repeat_penalty 1
clientv0.4.98+102
Set those in llama.cpp, then:
llm-benchmark benchmark --model "unsloth/Qwen3.8-27B-GGUF:UD-Q4_K_M" --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.