Benchmark result
qwen3.5-4B-super-coder.Q4_0 on NVIDIA GeForce RTX 4060 Laptop GPU — 66.1 tok/s
Measured with llama.cpp b11985-6d194531e on November 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 4060 Laptop GPU · median 66.1 tok/s.
sort
- 166.4tok/s45.5llama.cpp · Q4_0
- 266.1tok/s53.7llama.cpp · Q4_0this run
- 365.7tok/s51.8llama.cpp · Q4_0
Reproduce this run
toolllama.cpp b11985-6d194531e
modelqwen3.5-4B-super-coder.Q4_0 (Q4_0)
context32,768
think limitnone
samplingtemperature 0.6000000238418579 · top_p 0.949999988079071 · top_k 20 · min_p 0 · presence_penalty 0 · repeat_penalty 1
clientv0.4.98+102
Set those in llama.cpp, then:
llm-benchmark benchmark --model "qwen3.5-4B-super-coder.Q4_0" --tool "llama.cpp"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.