Benchmark result
nemotron-3.5-bolt:e4b on NVIDIA RTX 2000 Ada Generation Laptop GPU — 87.1 tok/s
Measured with Ollama 0.40.13 on November 1, 2026.
Support llm-bench.io
llm-bench.io is free. If it helped you, I'd appreciate your support to cover the infrastructure costs.
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 RTX 2000 Ada Generation Laptop GPU · median 85.7 tok/s.
sort
- 187.1tok/s72.3Ollama · Q4_K_Mthis run
- 285.7tok/s64.3Ollama · Q4_K_M
- 366.9tok/s65.9Ollama · Q4_K_M
nemotron-3.5-bolt:e4b on other hardware
- 85.1tok/s64.9NVIDIA RTX 3500 Ada Generation Laptop GPU · Q4_K_M
- 84.3tok/s71.5NVIDIA RTX 3500 Ada Generation Laptop GPU · Q4_K_M
- 82.6tok/s62.8NVIDIA RTX 3500 Ada Generation Laptop GPU · Q4_K_M
- 82.5tok/s72.3NVIDIA RTX 3500 Ada Generation Laptop GPU · Q4_K_M
- 82.2tok/s73.7NVIDIA RTX 3500 Ada Generation Laptop GPU · Q4_K_M
Reproduce this run
toolOllama 0.40.13
modelnemotron-3.5-bolt:e4b (Q4_K_M)
context8,192
thinkingon
samplingtemperature 1 · top_p 0.95 · top_k 64
clientv0.4.98+102
Set those in Ollama, then:
llm-benchmark benchmark --model "nemotron-3.5-bolt:e4b" --tool "Ollama"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.