Benchmark result
qwen3-coder:latest on AMD Radeon RX 7900 XTX — 33.1 tok/s
Measured with Ollama 0.20.7 on April 17, 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
2nd fastest of 2 runs of this model on AMD Radeon RX 7900 XTX · median 64.6 tok/s.
sort
- 196.0tok/s71.2Ollama · Q4_K_M
- 233.1tok/s57.5Ollama · Q4_K_Mthis run
qwen3-coder:latest on other hardware
Reproduce this run
toolOllama 0.20.7
modelqwen3-coder:latest (Q4_K_M)
context65,536
clientv0.4.15+90
Set those in Ollama, then:
llm-benchmark benchmark --model "qwen3-coder: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.