Benchmark result
qwen3:14b on AMD Radeon RX 7900 XTX — 11.6 tok/s
Measured with Ollama 0.20.7 on April 17, 2026.
How this run compares
3rd fastest of 3 runs of this model on AMD Radeon RX 7900 XTX · median 13.1 tok/s.
sort
- 116.5tok/s61.7Ollama · Q4_K_M
- 213.1tok/s61.5Ollama · Q4_K_M
- 311.6tok/s50.0Ollama · Q4_K_Mthis run
qwen3:14b on other hardware
Reproduce this run
toolOllama 0.20.7
modelqwen3:14b (Q4_K_M)
context8,192
clientv0.4.15+90
Set those in Ollama, then:
llm-benchmark benchmark --model "qwen3:14b" --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.