Nemotron 3.5 Bolt

Run everyday agentic tasks locally on a 24GB GPU

Product HuntArtificial IntelligenceLaunched Oct 17, 202611#27 of the day

About Nemotron 3.5 Bolt

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.

The people behind Nemotron 3.5 Bolt

We haven't found the people behind Nemotron 3.5 Bolt yet. New makers are added as we find them.

More Artificial Intelligence launches

ElevenLabs Realtime
Realtime voice agent models with 570ms to first audio
Oct 23, 2026
FLUX 3 Max
fal’s FLUX 3 Max: 10-second AI video in about 12 seconds
Oct 23, 2026
Avatar SDK Move | Lifelike AI Motion
Turn text into hyper-realistic motion for human avatars
Oct 23, 2026 · 1 person
Mistral Voxtral 3
Mistral’s speech models for transcription, TTS and agents
Oct 22, 2026 · 1 person
Voxelo 3.0
Phone video to photoreal 3D & JSON-LD in an hour
Oct 22, 2026 · 1 person
Notion Auto
Notion’s rebuilt Agents run for hours and cost far less
Oct 21, 2026

Made Nemotron 3.5 Bolt? Ask us to remove this listing or your details.