NVIDIA·NemotronHForCausalLM

NVIDIA Nemotron 3 Nano 4B BF16 — Hardware Requirements & GPU Compatibility

Chat

NVIDIA Nemotron 3 Nano 4B BF16 is a 4.0B-parameter open language model from NVIDIA. It supports a context window of up to 262,144 tokens. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.

342.4K downloads 90 likesMar 2026262K context

Based on NVIDIA Nemotron Nano 9B v2

Specifications

Publisher: NVIDIA
Parameters: 4.0B
Architecture: NemotronHForCausalLM
Context Length: 262,144 tokens
Vocabulary Size: 131,072
Release Date: 2026-03-20
License: Other

Get Started

HuggingFace

nvidia/NVIDIA-Nemotron-3-Nano-4B-BF16

No quantization data available.

Related Models

Derivatives (3)

NVIDIA Nemotron 3 Nano 4B BF16 GGUF NVIDIA Nemotron 3 Nano 4B BF16 I1 GGUF Nvidia.NVIDIA Nemotron 3 Nano 4B BF16 GGUF