Benchmark result
NVIDIA-Nemotron-3.5-Bolt-E4B-UD-Q4_K_XL on NVIDIA GeForce RTX 4060 Laptop GPU — 46.6 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 46.6 tok/s.
sort
- 147.8tok/s70.9llama.cpp · Q4_K
- 247.2tok/s67.0llama.cpp · Q4_K
- 347.0tok/s72.0llama.cpp · Q4_K
- 446.7tok/s72.9llama.cpp · Q4_K
- 546.6tok/s75.7llama.cpp · Q4_Kthis run
- 646.6tok/s69.4llama.cpp · Q4_K
- 746.3tok/s71.7llama.cpp · Q4_K
- 845.8tok/s72.3llama.cpp · Q4_K
- 944.7tok/s72.4llama.cpp · Q4_K
- 1044.0tok/s64.5llama.cpp · Q4_K
Reproduce this run
toolllama.cpp b11985-6d194531e
modelNVIDIA-Nemotron-3.5-Bolt-E4B-UD-Q4_K_XL (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" --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.