Benchmark result
Darwin-28B-REASON.i1-IQ3_XXS on AMD Radeon RX 7800 XT — 38.4 tok/s
Measured with llama.cpp b10805-86b351fd6 on October 6, 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 · median 38.4 tok/s.
sort
- 138.4tok/s71.2llama.cpp
- 238.4tok/s73.1llama.cppthis run
Reproduce this run
toolllama.cpp b10805-86b351fd6
modelDarwin-28B-REASON.i1-IQ3_XXS
context65,536
think limitnone
samplingtemperature 1 · top_p 0.949999988079071 · top_k 20 · min_p 0.05000000074505806 · presence_penalty 0 · repeat_penalty 1
clientv0.4.87+102
Set those in llama.cpp, then:
llm-benchmark benchmark --model "Darwin-28B-REASON.i1-IQ3_XXS" --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.