NVIDIA
The official handle for NVIDIA.
5.0•35 reviews•2.3K followers
The official handle for NVIDIA.
5.0•35 reviews•2.3K followers
NVIDIA, inventor of the GPU, which creates interactive graphics on laptops, workstations, mobile devices, notebooks, PCs, and more. We created the world’s largest gaming platform and the world’s fastest supercomputer. We are the brains of self-driving cars, intelligent machines, and IoT.
This is the 34th launch from NVIDIA. View more
Nemotron 3.5 Bolt
Launching today
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.
Free
Launch tags:Artificial Intelligence
Launch Team
Viktor.comAn AI coworker that actually does the work
Promoted
Big AI models are impressive, but running them locally without giving up too much speed or capability is still a challenge. NVIDIA is taking a shot at that with Nemotron 3.5 Bolt 74B-A9B 24GB.
The problem
Running capable AI agents locally usually means making trade-offs between model intelligence, speed, and memory. Larger models can be difficult to fit alongside your other applications, while smaller models may struggle with complex tasks.
The solution
Nemotron 3.5 Bolt is an open-weight vision-language model designed to fit within a 24GB memory budget and run everyday agentic workloads locally on NVIDIA RTX and DGX Spark systems.
What makes it different
Instead of training a small model from scratch, NVIDIA compresses a much larger model and uses aggressive 2-bit quantization to preserve more of its capabilities within a tight memory budget. It also uses speculative decoding to speed up generation.
What you get:
A 74B-parameter model with 9B active parameters
A 24GB memory footprint for local AI workloads
Around 84 tokens per second on NVIDIA's reported RTX Spark benchmark
Designed for agentic tasks such as web browsing, tool use, and terminal workflows
Open-weight checkpoints, including a version for further customization
NVIDIA reports #1 in PinchBench and #2 in WebArena and BrowseComp among models with similar memory footprints
Who it's for
Developers building local AI agents, experimenting with private workflows, automating research, or running coding and browsing agents without sending every task to the cloud.
Try it:
Explore the official NVIDIA announcement, get the model on Hugging Face, or check the technical report.