Benchmark result
Scion-35B-A3B-PQ2_0-corr on NVIDIA RTX A6000 — 100.8 tok/s
Measured with llama.cpp manual on October 23, 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.
Reproduce this run
toolllama.cpp manual
modelScion-35B-A3B-PQ2_0-corr (Q2_0)
context262,144
thinkingon
think limitnone
clientv0.4.96+102
Set those in llama.cpp, then:
llm-benchmark benchmark --model "Scion-35B-A3B-PQ2_0-corr" --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.