Benchmark result
qwen3.5-4b@q6_k on NVIDIA GeForce RTX 3060 Laptop GPU — 29.6 tok/s
Measured with Bionic manual on October 13, 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
1st fastest of 3 runs of this model on NVIDIA GeForce RTX 3060 Laptop GPU · median 28.8 tok/s.
sort
- 129.6tok/s75.2Bionic · Q6_Kthis run
- 228.8tok/s67.7Bionic · Q6_K
- 328.4tok/s71.6Bionic · Q6_K
Reproduce this run
toolBionic manual
modelqwen3.5-4b@q6_k (Q6_K)
context8,192
clientv0.4.92+102
Set those in Bionic, then:
llm-benchmark benchmark --model "qwen3.5-4b@q6_k" --tool "Bionic"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.