Benchmark result
ornith:35b-q8_0 on Apple M5 Max — 86.0 tok/s
Measured with Ollama 0.32.15 on August 21, 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.
Reproduce this run
toolOllama 0.32.15
modelornith:35b-q8_0 (Q8_0)
context65,536
clientv0.4.40+97
Set those in Ollama, then:
llm-benchmark benchmark --model "ornith:35b-q8_0" --tool "Ollama"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.