Benchmark result
model on NVIDIA GeForce RTX 3060 — 84.1 tok/s
Measured with llama.cpp b11941-19ff817fb on October 27, 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 NVIDIA GeForce RTX 3060 · median 68.9 tok/s.
sort
- 184.1tok/s61.5llama.cppthis run
- 253.7tok/s83.9llama.cpp
Reproduce this run
toolllama.cpp b11941-19ff817fb
modelmodel
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
clientv0.4.98+102
Set those in llama.cpp, then:
llm-benchmark benchmark --model "model" --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.