Benchmark result
unsloth/gemma-4-31B-it-qat-GGUF:UD-Q4_K_XL on NVIDIA GeForce RTX 3080 Ti +1 more — 46.4 tok/s
Measured with llama.cpp b10502-0adcc3bb5 on August 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
2nd fastest of 2 runs of this model on NVIDIA GeForce RTX 3080 Ti +1 more · Multi-GPU · median 47.1 tok/s.
- 147.8tok/s65.3llama.cpp · Q4_K
- 246.4tok/s72.1llama.cpp · Q4_Kthis run
unsloth/gemma-4-31B-it-qat-GGUF:UD-Q4_K_XL on other hardware
Reproduce this run
Set those in llama.cpp, then:
llm-benchmark benchmark --model "unsloth/gemma-4-31B-it-qat-GGUF:UD-Q4_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.