Nemotron 3.5 Bolt
Early signalRun everyday agentic tasks locally on a 24GB GPU
Launched 27d ago
Signal
28
Velocity
13
What this means
Rising steadily
Steady upward velocity sustained.
Prediction
Top-5 finish probability
13%
today
Projected end-of-day votes
11range 8–15
Trajectory
rising
Steady upward velocity sustained.
Speed vs peers
0.8×
244 AI Agents launches
About
Nemotron 3.5 Bolt 24GB is NVIDIA’s model for running everyday agentic tasks locally on NVIDIA RTX and DGX Spark hardware. It compresses Nemotron 3.5 Super VL from 120B total, 12B active to 74B total, 9B active, sized to fit a 24GB memory budget. NVIDIA reports 84 tokens per second on RTX Spark. Text and vision. Checkpoints, GGUF files, and a speculative-decoding drafter are on Hugging Face.
AI Summary
The Nemotron 3.5 Bolt is an NVIDIA model designed for running everyday agentic tasks locally on 24GB GPU hardware, optimized to fit within a 24GB memory budget. It offers a compression of the original Nemotron 3.5 Super VL model and achieves a processing speed of 84 tokens per second on RTX Spark.
Attention & discussion velocity
Performance
Velocity13
Vote pace vs average
Momentum13
Sustained over 6h
Virality15
Spread × engagement
Engagement18
Discussion per unit of attention
Signal sources
2 of 6 active- Launch tracking9 readings since we picked it up
- AI analysisAI Agents
- Comment intelligencethread not yet analysed
- Outside discussionnot checked — domain is a storefront or shared
- Revenue signalsno match on this domain
- Editorial scoringbelow the signal threshold for this pass
A source that found nothing is a measurement. A source that has not run is a gap. Neither means the launch lacks the thing.