NVIDIANVIDIA

Nemotron 3 Nano 30B

Frontier
Jun 2025Veröffentlicht131K TokenKontextNVIDIA Open ModelLizenz93 HerausragendQualität

Nemotron 3 Nano 30B (30B parameters) requires approximately 22.5 GB of VRAM with Q4_K_M quantization. For the best balance of quality and speed, we recommend hardware with at least 26 GB of VRAM.

Loslegen

— kopieren & einfügen, um lokal auszuführen

Copy-paste commands to run Nemotron 3 Nano 30B on your machine.

Run

ollama run nemotron-nano:30b

Quick specs

Parameters30B
Architecturedense
Context131K tokens
Modalitytext
Min RAM11.7 GB
Rec. RAM18.3 GB (Q4_K_M)
LicenseNVIDIA Open Model
FamilyNemotron
Code Chat Reasoning

About this model

Nemotron 3 Nano 30B is NVIDIA's mid-size reasoning model delivering strong performance across coding, math, and agentic tasks. Fits on a 24 GB GPU at Q4_K_M.

  • Strong reasoning — competitive with 70B-class models on key benchmarks
  • Fits on RTX 4090 / RTX 5090 at Q4_K_M
  • Agentic and tool-use capabilities

Verwandte Modelle

Deine Hardware

Erkennung...

Schnellauswahl

Beste Hardware

Top-Empfehlungen für Nemotron 3 Nano 30B

Dieses Modell ausführen

Quantisierungsoptionen

VRAM-Schätzungen nach Quantisierungsstufe

No hardware detected — fit column shows raw VRAM estimates

QuantBitsVRAMQualityFit
Q2_K
2
11.7 GB
Low
Q3_K_S
3
14.7 GB
Low
NVFP4
4
16.8 GB
Medium
Q4_K_M
4
18.3 GB
Medium
Q5_K_M
5
21.6 GB
High
Q6_K
6
24.6 GB
High
Q8_0
8
32.1 GB
Very High
F16
16
61.5 GB
Maximum

Quality benchmarks

Nemotron 3 Nano 30B benchmark scores

Benchmark verified

Reasoning

MMLU-Pro78.3%
GPQA Diamond73.0%
MATH-500
ARC Challenge

Source: official · 2025-12-25

Hardware-Kompatibilität

Eignungsschätzungen für alle Hardware

Rechner öffnen

Computing compatibility...

Speicheraufschlüsselung

Reference: RTX 2060 6GB

Weights18.3 GB
KV Cache2.4 GB
Runtime1.2 GB
Headroom0.6 GB

Häufig gestellte Fragen

FAQ — Nemotron 3 Nano 30B

Siehe auch