Benchmark result
qwen3:14b on NVIDIA GeForce RTX 5060 Ti — 204.2 tok/s
Measured with Ollama manual on October 1, 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 3 runs of this model on NVIDIA GeForce RTX 5060 Ti · median 204.2 tok/s.
sort
- 1224.6tok/s53.3Ollama · Q4_K_M
- 2204.2tok/s54.3Ollama · Q4_K_Mthis run
- 3138.8tok/s52.6Ollama · Q4_K_M
Reproduce this run
toolOllama manual
modelqwen3:14b (Q4_K_M)
context16,384
thinkingon
samplingtemperature 0.6 · top_p 0.95 · top_k 20 · repeat_penalty 1
clientv0.4.85+101
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.