Benchmark result
unsloth/NVIDIA-Nemotron-3.5-Bolt-E4B-GGUF on NVIDIA GeForce RTX 4070 — 87.9 tok/s
Measured with Unsloth Studio on October 28, 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
4th fastest of 4 runs of this model on NVIDIA GeForce RTX 4070 · median 131.3 tok/s.
sort
- 1133.9tok/s72.1Unsloth Studio · UD-Q4_K_XL · KV q8_0
- 2133.2tok/s70.4Unsloth Studio · UD-Q4_K_XL · KV q8_0
- 3129.4tok/s64.0Unsloth Studio · UD-Q4_K_XL · KV q4_0
- 487.9tok/s69.3Unsloth Studio · UD-Q4_K_XL · KV q4_0this run
Reproduce this run
toolUnsloth Studio
modelunsloth/NVIDIA-Nemotron-3.5-Bolt-E4B-GGUF (UD-Q4_K_XL)
context262,144
kv cacheq4_0
thinkingon
think limitnone
samplingtemperature 1 · top_p 0.95 · top_k -1 · min_p 0.01 · presence_penalty 0
clientv0.4.98+102
Set those in Unsloth Studio, then:
llm-benchmark benchmark --model "unsloth/NVIDIA-Nemotron-3.5-Bolt-E4B-GGUF" --tool "Unsloth Studio"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.