Benchmark result
byteshape/Qwen3.8-27B-GGUF:IQ3_XS on AMD Radeon RX 7800 XT +1 more — 45.3 tok/s
Measured with llama.cpp b12033-785322d17 on November 7, 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 2 runs of this model on AMD Radeon RX 7800 XT +1 more · Multi-GPU · median 45.5 tok/s.
sort
- 145.8tok/s84.8llama.cpp
- 245.3tok/s82.6llama.cppthis run
Reproduce this run
toolllama.cpp b12033-785322d17
modelbyteshape/Qwen3.8-27B-GGUF:IQ3_XS
context128,000
thinkingon
effortmedium
think limitnone
samplingtemperature 1 · top_p 0.949999988079071 · top_k 20 · min_p 0 · presence_penalty 0 · repeat_penalty 1
clientv0.4.99+102
Set those in llama.cpp, then:
llm-benchmark benchmark --model "byteshape/Qwen3.8-27B-GGUF:IQ3_XS" --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.