Benchmark result
Sage-A1.5_t1p95k20m0P15 on 2× Tesla V100-PCIE-32GB — 92.7 tok/s
Measured with llama.cpp manual on November 10, 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.
How this run compares
2nd fastest of 2 runs of this model on 2× Tesla V100-PCIE-32GB · Multi-GPU · median 93.0 tok/s.
sort
- 193.3tok/s80.1llama.cpp
- 292.7tok/s71.8llama.cppthis run
Reproduce this run
toolllama.cpp manual
modelSage-A1.5_t1p95k20m0P15
context32,768
think limit8,096 tokens
samplingtemperature 1 · top_p 0.949999988079071 · top_k 20 · min_p 0 · presence_penalty 1.5 · repeat_penalty 1
clientv0.4.99+102
Set those in llama.cpp, then:
llm-benchmark benchmark --model "Sage-A1.5_t1p95k20m0P15" --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.