Benchmark result
hf.co/unsloth/gemma-4-26B-A4B-it-GGUF:UD-IQ3_S on Advanced Micro Devices, Inc. [AMD/ATI] Device 7590 — 71.0 tok/s
Measured with Ollama 0.33.1 on November 21, 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
3rd fastest of 3 runs of this model on Advanced Micro Devices, Inc. [AMD/ATI] Device 7590 · median 71.1 tok/s.
sort
- 171.4tok/s66.5Ollama · IQ3_S
- 271.1tok/s76.8Ollama · IQ3_S
- 371.0tok/s71.1Ollama · IQ3_Sthis run
Reproduce this run
toolOllama 0.33.1
modelhf.co/unsloth/gemma-4-26B-A4B-it-GGUF:UD-IQ3_S (IQ3_S)
context16,384
thinkingon
clientv0.4.99+102
Set those in Ollama, then:
llm-benchmark benchmark --model "hf.co/unsloth/gemma-4-26B-A4B-it-GGUF:UD-IQ3_S" --tool "Ollama"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.