Nemotron 3.5 — local AI model by NVIDIA

Written by Jakub Rusinowski · Last updated

NVIDIA's agentic line, built on a hybrid stack that interleaves Mamba-2 state-space layers and MoE blocks with a minority of attention layers. Only the attention layers hold a KV cache, which is what lets it advertise a 1M-token context at this size.

Variants

The smallest Nemotron 3.5 variant needs about 7 GB of VRAM at Q4_K_M — quantized weights plus framework overhead, before any KV cache.

ModelVRAM
Nemotron 3.5 Lightning 30B-A3B →
30B (3B active)
~18.9 GB
Nemotron 3.5 Bolt 74B →
74B (9B active)
~22.8 GB
Nemotron 3.5 Super VL 120B-A12B →
120B (12B active)
~73.3 GB
Nemotron 3.5 Bolt E4B →
8B (4B effective)
~7 GB

Memory is quantized weights plus overhead at Q4_K_M, from the same engine as the GPU & VRAM checker.

How to run Nemotron 3.5 locally

Install Ollama, then pull the tag.

ollama run nemotron-3.5-lightning:30b

Pick a size above for its own VRAM figure, speed estimate and install command.

Licence

OpenMDW-1.1Commercial use permitted

Commercial use permitted. No usage restrictions beyond attribution.

Applies to: Nemotron 3.5 Lightning 30B-A3B, Nemotron 3.5 Bolt 74B, Nemotron 3.5 Super VL 120B-A12B, Nemotron 3.5 Bolt E4B

Recommended GPU

The cheapest catalogued GPU that runs Nemotron 3.5 locally (min 7 GB VRAM) is the Intel Arc B570 (10 GB).

Affiliate disclosure: Some links on this page are affiliate links — if you buy through them, LLM Configurator may earn a commission at no extra cost to you. As an Amazon Associate, LLM Configurator earns from qualifying purchases.
Intel Arc B570 10GB
10 GB VRAM · 150 W board power
2026 prices are volatile — check the current listing.

Can I run Nemotron 3.5 on my GPU?

Nemotron 3.5 — frequently asked questions

How much VRAM does Nemotron 3.5 need?

Nemotron 3.5 needs about 7 GB VRAM at Q4_K_M quantization for its smallest variant. Variants: Nemotron 3.5 Lightning 30B-A3B (19 GB, Q4_K_M); Nemotron 3.5 Bolt 74B (23 GB, IQ2_XXS QAD); Nemotron 3.5 Super VL 120B-A12B (73 GB, Q4_K_M); Nemotron 3.5 Bolt E4B (7 GB, Q4_K_M). On Apple Silicon, unified memory counts toward this requirement.

Can I run Nemotron 3.5 on an RTX 4090 (24 GB)?

Yes — Nemotron 3.5 runs on an RTX 4090 (24 GB) and other 24 GB cards such as the RTX 3090. Smaller variants also fit comfortably on 8–16 GB GPUs at Q4_K_M.

What quantization should I use for Nemotron 3.5?

Q4_K_M is the best balance of quality and VRAM for Nemotron 3.5 in most cases. Choose Q8_0 for near-lossless quality if you have spare VRAM, or smaller quants (Q3/Q2) only when memory is tight.

How do I run Nemotron 3.5 with Ollama?

Install Ollama, then run: ollama run nemotron-3.5-lightning:30b. This downloads Nemotron 3.5 and starts a local, OpenAI-compatible endpoint — no internet connection is needed after the initial download.