The AI Loadout
←Back to models
Checked Active: 2026-10-16
NVIDIA

Nemotron 3.5 Bolt 74B-A9B (local)

NVIDIA's local agent model for a single 24 GB NVIDIA GPU: coding, tool use, and reading screenshots, charts and documents.

Evaluation Analysis: Vision, tools and thinking (on or off). 74B total and 9B active parameters, shipped by NVIDIA in 2-bit form so it fits about 24 GB. NVIDIA GPUs only for now: Ollama says Apple Silicon is not supported yet. Needs Ollama 0.40.5 or later. Released Oct 15, 2026.
Context Window256K
Input Price / 1MFree (local)
Output Price / 1MFree (local)
Release Date2026-10-15

Run it locally

ollama run nemotron-3.5-bolt
Ollama tag
nemotron-3.5-bolt (74b-a9b)
LM Studio name
nvidia/nemotron-3.5-bolt-74b-a9b
Download size by quantization
25 GB download (Ollama); LM Studio lists 22 GB minimum memory
License
OpenMDW 1.1

Memory needed is roughly the download size plus 2 to 4 GB for context. See how to run AI locally.

Specs and prices checked 2026-10-16 against the official page.

Used in these setups

Related skills and personas

Agent skills and bot personas that pair well with Nemotron 3.5 Bolt 74B-A9B (local).

Browse full directories:All Skills (>35)·All Personas (>15)

Want tested skills and personas installed in one command? See the AI Loadout packs, from $9.