Benchmark result
Gryphe/Gemma-4-31B-StyleTune:MY-Q6_K_XL on NVIDIA GeForce RTX 3080 Ti +1 more — 23.9 tok/s
Measured with llama.cpp b11989-78febbad9 on October 30, 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
2nd fastest of 2 runs of this model on NVIDIA GeForce RTX 3080 Ti +1 more · Multi-GPU · median 24.3 tok/s.
sort
- 124.6tok/s73.6llama.cpp · Q6_K
- 223.9tok/s75.8llama.cpp · Q6_Kthis run
Reproduce this run
toolllama.cpp b11989-78febbad9
modelGryphe/Gemma-4-31B-StyleTune:MY-Q6_K_XL (Q6_K)
context65,536
thinkingon
think limitnone
samplingtemperature 1 · top_p 0.949999988079071 · top_k 64 · min_p 0 · presence_penalty 0 · repeat_penalty 1
clientv0.4.98+102
Set those in llama.cpp, then:
llm-benchmark benchmark --model "Gryphe/Gemma-4-31B-StyleTune:MY-Q6_K_XL" --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.