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 Airline
48.0%自報
Multi-Challenge
38.5%自報
Communication
Tau2 Retail
56.9%自報
Tau2 Telecom
42.2%自報
General
Arena-Hard v2
67.7%自報
Language
WMT24++
86.2%自報
MMLU-Pro
78.3%自報
MMLU-ProX
59.5%自報
Math
AIME 2025
99.2%自報
Reasoning
GPQANYU + Cohere + Anthropic (2023)
75.0%自報
LiveCodeBench v6
68.3%自報
SWE-Bench Verified
38.8%自報
SciCode
33.3%自報
Humanity's Last Exam
15.5%自報
Terminal-Bench
8.5%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))Language70
Legal70
Finance70
Healthcare70
Creativity70
Writing70
Math60
Physics50
Reasoning50
General50
Biology50
Chemistry50
Communication50
Tool Calling50
Chat40
Frontend Development40
Code30
Vision20
Agents10
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。