How to run NVIDIA's AI on your computer, with no internet

Nemotron 3.5 Bolt is an NVIDIA model that is free to download and runs on your computer offline.

Steps

  1. Download LM Studio, which is free: lmstudio.ai/download.
  2. Open it, search for "Nemotron 3.5 Bolt" and download the one from NVIDIA. This is the direct link: lmstudio.ai/nvidia/nemotron-3.5-bolt-e4b.
  3. Load it in the chat, turn off the wifi and ask it anything.

What Nemotron 3.5 Bolt is

NVIDIA released it on October 23, 2026. It starts from Gemma 4 E4B, Google's small model, and NVIDIA trained it to hold a conversation and use tools on the device itself: voice assistants, video game characters and robots. In NVIDIA's tests it scores about 40% higher on average than Nemotron 3 Nano 4B, its previous model of that size.

Specs

SpecValue
ReleasedOctober 23, 2026
Made byNVIDIA, starting from Google's Gemma 4 E4B
Download6.18 GB (GGUF format, Q4_K_M version)
Parameters7.5 billion
Memory it usesBetween 3.1 and 5 GB, depending on the machine
Context64,000 tokens
Languages35, Spanish among them
LicenseOpenMDW-1.1
Downloads172,000 in the last month on Hugging Face, as of November 19, 2026

How fast it runs

MachineTokens per secondMemory used
RTX 5070 (12 GB)1333.5 GB
RTX Spark (32 GB)673.1 GB
Jetson AGX Orin (32 GB)244.2 GB
Jetson Orin Nano (8 GB)15.54.2 GB

These are NVIDIA's measurements with the Q4_K_M version on llama.cpp, with a 3,000-token input and a 50-token answer. The data comes from research.nvidia.com and the model card on Hugging Face.