Benchmark result
devstral-small-2:latest on AMD Radeon RX 7900 XTX — 11.8 tok/s
Measured with Ollama 0.21.1 on April 25, 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
1st fastest of 2 runs of this model on AMD Radeon RX 7900 XTX · median 11.1 tok/s.
sort
- 111.8tok/s62.5Ollama · Q4_K_Mthis run
- 210.4tok/s65.8Ollama · Q4_K_M
Reproduce this run
toolOllama 0.21.1
modeldevstral-small-2:latest (Q4_K_M)
context65,536
clientv0.4.20+97
Set those in Ollama, then:
llm-benchmark benchmark --model "devstral-small-2: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.