Will It Run AI

NVIDIANVIDIA

Nemotron 3 Nano 30B

前沿
Jun 2025发布日期131K tokens上下文NVIDIA Open Model许可证93 卓越质量

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.

快速开始

— 复制粘贴即可本地运行

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 是 NVIDIA 的中等规模推理模型,在编程、数学和智能体任务方面表现强劲。使用 Q4_K_M 量化可在 24 GB GPU 上运行。

  • 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

相关模型

你的硬件

检测中...

快速推荐

最佳硬件

Nemotron 3 Nano 30B 的最佳选择

运行此模型

量化选项

各量化级别的 VRAM 估算

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

硬件兼容性

全部硬件的适配估算

打开计算器

Computing compatibility...

内存详细分析

Reference: RTX 2060 6GB

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

常见问题

FAQ — Nemotron 3 Nano 30B

另请参阅