Benchmark result
ministral-3:14b on AMD Radeon RX 7900 XTX — 41.6 tok/s
Measured with Ollama 0.20.7 on April 16, 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
6th fastest of 6 runs of this model on AMD Radeon RX 7900 XTX · median 42.2 tok/s.
sort
- 143.0tok/s66.3Ollama · Q4_K_M
- 243.0tok/s66.0Ollama · Q4_K_M
- 342.7tok/s69.2Ollama · Q4_K_M
- 441.6tok/s57.6Ollama · Q4_K_M
- 541.6tok/s73.0Ollama · Q4_K_M
- 641.6tok/s68.4Ollama · Q4_K_Mthis run
Reproduce this run
toolOllama 0.20.7
modelministral-3:14b (Q4_K_M)
context65,536
clientv0.4.8+85
Set those in Ollama, then:
llm-benchmark benchmark --model "ministral-3:14b" --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.