Benchmark result
default on NVIDIA GeForce RTX 4070 — 71.0 tok/s
Measured with llama.cpp b15430-374a89e75 on November 20, 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
1st fastest of 4 runs of this model on NVIDIA GeForce RTX 4070 · median 68.6 tok/s.
sort
- 171.0tok/s87.4llama.cppthis run
- 269.8tok/s78.1llama.cpp
- 367.4tok/s83.1llama.cpp
- 466.7tok/s82.9llama.cpp
Reproduce this run
toolllama.cpp b15430-374a89e75
modeldefault
context65,536
thinkingon
effortmedium
think limitnone
samplingtemperature 1 · top_p 0.949999988079071 · top_k 20 · min_p 0 · presence_penalty 0 · repeat_penalty 1
clientv0.4.99+102
Set those in llama.cpp, then:
llm-benchmark benchmark --model "default" --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.