Benchmark result
Jan-v3.5-4B-Q4_K_XL on NVIDIA GeForce RTX 3060 Laptop GPU — 75.3 tok/s
Measured with Jan manual on October 27, 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 73.4 tok/s.
sort
- 175.3tok/s66.8Jan · Q4_Kthis run
- 273.4tok/s68.2Jan · Q4_K
- 371.6tok/s66.1Jan · Q4_K
Reproduce this run
toolJan manual
modelJan-v3.5-4B-Q4_K_XL (Q4_K)
context8,192
clientv0.4.98+102
Set those in Jan, then:
llm-benchmark benchmark --model "Jan-v3.5-4B-Q4_K_XL" --tool "Jan"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.