Benchmark result
lfm3-1.7b on Tesla P100-PCIE-16GB +1 more — 76.5 tok/s
Measured with llama.cpp manual on November 9, 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
lfm3-1.7b on other hardware
Reproduce this run
toolllama.cpp manual
modellfm3-1.7b
context65,536
think limitnone
samplingtemperature 0.10000000149011612 · top_p 0.949999988079071 · top_k 50 · min_p 0.05000000074505806 · presence_penalty 0 · repeat_penalty 1.100000023841858
clientv0.4.99+102
Set those in llama.cpp, then:
llm-benchmark benchmark --model "lfm3-1.7b" --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.