跳轉到主要內容

NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning)

NVIDIA開源權重NVIDIA Open Model License Agreement · 商用許可

描述

Nemotron 3 Nano is a 31.6B hybrid MoE model optimized for fast, long‑context agentic reasoning. It mixes Mamba‑2 and Transformer layers with a sparse MoE router (~3.6B active params per token) to deliver up to 4× higher throughput than Nemotron 2 and strong accuracy across math, coding, and tools. It supports a 1M‑token context window, offers Reasoning ON/OFF and a thinking‑budget to control costs, and ships with open weights, data, and RL tooling (NeMo Gym/RL). Released Dec 15, 2025 under the NVIDIA Open Model License, it’s built as the efficient backbone for multi‑agent systems at scale.

發布日期
2025-12-15
參數規模
32.0B
上下文長度
262K
支援模態
text

能力雷達圖

50
general
30
coding
60
reasoning
43
science估算
50
agents
0
multimodal

缺少專門科學評測時,Science 由 LLM Stats 科學得分或推理能力估算。

排行榜排名

暫無排名資料

基準測試分數 (LLM Stats)

(LLM Stats (zeroeval))

Chat

Tau2 Airline48.0%自報
Multi-Challenge38.5%自報

Communication

Tau2 Retail56.9%自報
Tau2 Telecom42.2%自報

General

Arena-Hard v267.7%自報

Language

WMT24++86.2%自報
MMLU-Pro78.3%自報
MMLU-ProX59.5%自報

Math

AIME 202599.2%自報

Reasoning

GPQANYU + Cohere + Anthropic (2023)75.0%自報
LiveCodeBench v668.3%自報
SWE-Bench Verified38.8%自報
SciCode33.3%自報
Humanity's Last Exam15.5%自報
Terminal-Bench8.5%自報

AA 評測指數

(Artificial Analysis)

暫無 AA 評測資料

LLM Stats 分類評分

(LLM Stats (zeroeval))
Language
70
Legal
70
Finance
70
Healthcare
70
Creativity
70
Writing
70
Math
60
Physics
50
Reasoning
50
General
50
Biology
50
Chemistry
50
Communication
50
Tool Calling
50
Chat
40
Frontend Development
40
Code
30
Vision
20
Agents
10

定價

輸入價格$0.05 / 1M tokens
輸出價格$0.2 / 1M tokens
混合價格(3:1)$0.0875 / 1M tokens
快取讀取價格$0.012 / 1M tokens

速度

Tokens/秒312.0
首Token延遲0.54s
首回答延遲0.54s

供應商價格排行

供應商價格排行

4 個供應商

最便宜: NVIDIA最貴: Venice AI
供應商輸入輸出
1NVIDIA主要
$0.05
$0.2
2DeepInfra
$0.05
$0.2
3Cortecs
$0.06
$0.24
4Venice AI
$0.075
$0.3

比較該模型在不同 API 供應商之間的定價。

外部連結