Benchmark result
qwen3.8:27b on AMD Radeon RX 7900 XTX — 37.6 tok/s
Measured with Ollama 0.32.14 on August 18, 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.
How this run compares
4th fastest of 5 runs of this model on AMD Radeon RX 7900 XTX · median 39.4 tok/s.
sort
- 151.8tok/s45.1LM Studio
- 239.4tok/s80.7Ollama · Q4_K_M
- 339.4tok/s81.0Ollama · Q4_K_M
- 437.6tok/s82.4Ollama · Q4_K_Mthis run
- 537.3tok/s84.5Ollama · Q4_K_M
Reproduce this run
toolOllama 0.32.14
modelqwen3.8:27b (Q4_K_M)
context65,536
clientv0.4.36+97
Set those in Ollama, then:
llm-benchmark benchmark --model "qwen3.8:27b" --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.