Benchmark result
ornith-1.5:35b-a3b on AMD Radeon RX 9060 XT — 95.8 tok/s
Measured with llama.cpp manual on October 20, 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 9060 XT · median 95.6 tok/s.
sort
- 195.8tok/s77.1llama.cppthis run
- 295.4tok/s69.8llama.cpp
ornith-1.5:35b-a3b on other hardware
Reproduce this run
toolllama.cpp manual
modelornith-1.5:35b-a3b
context32,768
thinkingoff
samplingtemperature 0.6000000238418579 · top_p 0.949999988079071 · top_k 20 · min_p 0.05000000074505806 · presence_penalty 0 · repeat_penalty 1
clientv0.4.96+102
Set those in llama.cpp, then:
llm-benchmark benchmark --model "ornith-1.5:35b-a3b" --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.