Benchmark result
gemma4:12b on Advanced Micro Devices, Inc. [AMD/ATI] Device 7590 — 33.8 tok/s
Measured with Ollama 0.33.1 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
gemma4:12b on other hardware
- 108.4tok/s71.1NVIDIA GeForce RTX 4070 Ti · Q4_K_M
- 63.1tok/s72.4AMD Radeon RX 7900 XTX · Q4_K_M
- 51.0tok/s70.6AMD Radeon RX 7600/7600 XT/7600M XT/7600S/7700S / PRO W7600 +1 more · Q4_K_M
- 49.3tok/s74.0NVIDIA RTX 3500 Ada Generation Laptop GPU · Q4_K_M
- 49.0tok/s73.6NVIDIA RTX 3500 Ada Generation Laptop GPU · Q4_K_M
Reproduce this run
toolOllama 0.33.1
modelgemma4:12b (Q4_K_M)
context32,768
thinkingon
samplingtemperature 1 · top_p 0.95 · top_k 64
clientv0.4.99+102
Set those in Ollama, then:
llm-benchmark benchmark --model "gemma4:12b" --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.