Benchmark result
./gemma-4-31B-it-AWQ4-styletune-head on NVIDIA GeForce RTX 3080 Ti +1 more — 32.1 tok/s
Measured with sglang manual on October 24, 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.
Reproduce this run
toolsglang manual
model./gemma-4-31B-it-AWQ4-styletune-head
context262,144
thinkingon
clientv0.4.97+102
Set those in sglang, then:
llm-benchmark benchmark --model "./gemma-4-31B-it-AWQ4-styletune-head" --tool "sglang"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.