Benchmark result
gemma3:latest on Intel Arc B390 — 20.8 tok/s
Measured with Ollama 0.40.0 on October 8, 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
4th fastest of 4 runs of this model on Intel Arc B390 · median 21.8 tok/s.
sort
- 125.0tok/s55.5Ollama · Q4_K_M
- 221.9tok/s53.0Ollama · Q4_K_M
- 321.6tok/s49.6Ollama · Q4_K_M
- 420.8tok/s54.1Ollama · Q4_K_Mthis run
Reproduce this run
toolOllama 0.40.0
modelgemma3:latest (Q4_K_M)
context65,536
samplingtemperature 1 · top_p 0.95 · top_k 64
clientv0.4.89+102
Set those in Ollama, then:
llm-benchmark benchmark --model "gemma3:latest" --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.