Benchmark result
NVIDIA-Nemotron-3.5-Bolt-E4B-UD-Q4_K_XL-DFLASH-NVFP4 on NVIDIA GeForce RTX 4060 Laptop GPU — 61.5 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
5th fastest of 10 runs of this model on NVIDIA GeForce RTX 4060 Laptop GPU · median 60.9 tok/s.
sort
- 165.6tok/s66.0llama.cpp · Q4_K
- 264.6tok/s69.4llama.cpp · Q4_K
- 362.7tok/s72.1llama.cpp · Q4_K
- 462.2tok/s69.5llama.cpp · Q4_K
- 561.5tok/s65.5llama.cpp · Q4_Kthis run
- 660.3tok/s66.5llama.cpp · Q4_K
- 759.6tok/s71.2llama.cpp · Q4_K
- 858.9tok/s76.3llama.cpp · Q4_K
- 957.7tok/s66.9llama.cpp · Q4_K
- 1057.6tok/s67.0llama.cpp · Q4_K
Reproduce this run
toolllama.cpp b11985-6d194531e
modelNVIDIA-Nemotron-3.5-Bolt-E4B-UD-Q4_K_XL-DFLASH-NVFP4 (Q4_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-UD-Q4_K_XL-DFLASH-NVFP4" --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.