Benchmark result
ornith:9b on NVIDIA RTX 3500 Ada Generation Laptop GPU — 44.4 tok/s
Measured with Ollama 0.40.15 on November 12, 2026.
Support llm-bench.io
llm-bench.io is free. If it helped you, I'd appreciate your support to cover the infrastructure costs.
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
8th fastest of 13 runs of this model on NVIDIA RTX 3500 Ada Generation Laptop GPU · median 45.2 tok/s.
sort
- 147.3tok/s69.1Ollama · Q4_K_M
- 246.2tok/s71.6Ollama · Q4_K_M
- 345.8tok/s75.1Ollama · Q4_K_M
- 445.2tok/s68.5Ollama · Q4_K_M
- 545.2tok/s67.6Ollama · Q4_K_M
- 645.2tok/s67.4Ollama · Q4_K_M
- 745.2tok/s68.4Ollama · Q4_K_M
- 844.4tok/s75.6Ollama · Q4_K_Mthis run
- 944.3tok/s65.3Ollama · Q4_K_M
- 1044.1tok/s66.6Ollama · Q4_K_M
- 1143.6tok/s74.1Ollama · Q4_K_M
- 1243.4tok/s63.5Ollama · Q4_K_M
- 1342.4tok/s60.4Ollama · Q4_K_M
ornith:9b on other hardware
Reproduce this run
toolOllama 0.40.15
modelornith:9b (Q4_K_M)
context32,768
thinkingon
samplingtemperature 0.6 · top_p 0.95 · top_k 20
clientv0.4.99+102
Set those in Ollama, then:
llm-benchmark benchmark --model "ornith:9b" --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.