Nemotron 3.5 Bolt
loaded
judge
Hosted on our own DGX Spark in Austria, available through an OpenAI-compatible API.
79
Logic Index · no budget field
70 t/s
tokens per second here
€ 0.75 / € 3
euros per M tokens, input / output
10M free tokens
Try Nemotron 3.5 Bolt for free
Every new account starts with 10M free tokens, usable for this and every other model. No card, no subscription.
Fact sheet
- Model name in the API
- nemotron-3.5-bolt
- Size
- 74B / 9B MoE (IQ2_XXS (QAD))
- Context
- 256K
- Input
- Text, Image
- Capabilities
- ToolsImageReasoning
- License
- OpenMDW-1.1
- Tier
- Multimodal
- Hosting
- always loaded
Call
OpenAI-compatible. The alias works as model name too.
{
"model": "judge",
"messages": [ … ]
}
Logic Index
All models in the Logic Index →By test area
Reasoning chains
78
Logic vs. world knowledge
98
Logic grid puzzles
59
Consistency: same answer in every run for 90% of tasks.
On hard puzzles Bolt often thinks up to the limit of 32,768 tokens without answering (37 of 120 puzzles). Scored as an error.
Speed over time
Operations of the Sparks →Tokens per second from our nightly measurement. Latest: 70 t/s.