Benchmark result
NVIDIA-Nemotron-3.5-Bolt-E4B-Q6_K-DFLASH-BF16 on NVIDIA GeForce RTX 4060 Laptop GPU — 63.0 tok/s
Measured with llama.cpp b11985-6d194531e on October 30, 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 5 runs of this model on NVIDIA GeForce RTX 4060 Laptop GPU · median 61.0 tok/s.
sort
- 163.5tok/s73.0llama.cpp · Q6_K
- 263.0tok/s74.9llama.cpp · Q6_Kthis run
- 361.0tok/s70.5llama.cpp · Q6_K
- 459.4tok/s70.9llama.cpp · Q6_K
- 558.7tok/s71.6llama.cpp · Q6_K
Reproduce this run
toolllama.cpp b11985-6d194531e
modelNVIDIA-Nemotron-3.5-Bolt-E4B-Q6_K-DFLASH-BF16 (Q6_K)
context32,768
think limitnone
samplingtemperature 0.800000011920929 · top_p 0.949999988079071 · top_k 40 · min_p 0.05000000074505806 · presence_penalty 0 · repeat_penalty 1
clientv0.4.98+102
Set those in llama.cpp, then:
llm-benchmark benchmark --model "NVIDIA-Nemotron-3.5-Bolt-E4B-Q6_K-DFLASH-BF16" --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.