NVIDIA
Run everyday agentic tasks locally on a 24GB GPU
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.
NVIDIA is a Artificial Intelligence company. It has launched 4 products on Product Hunt; the most upvoted was NVIDIA PersonaPlex (278 upvotes). Adamlead has 1 person on file at NVIDIA.
NVIDIA timeline
- Run everyday agentic tasks locally on a 24GB GPU
- Powers faster, efficient reasoning for long-running agents
- The GPT moment for real-time computer graphics
- Natural Conversational AI With Any Role and Voice
People at NVIDIA
Emails are shown masked, with whether each one has been verified. They're unlocked in the app with Lifetime access.
| Name | Title | |
|---|---|---|
Maker | – |
Frequently asked questions
Who works at NVIDIA?
Adamlead has 1 person on file at NVIDIA, including Sungwon Kim (Maker). Each email shows whether it has been verified.