About
NVIDIA-Nemotron-Nano-9B-v2 is a large language model (LLM) trained from scratch by NVIDIA, and designed as a unified model for both reasoning and non-reasoning tasks. It responds to user queries and...
Related Models
NVIDIA Nemotron 3 Nano 4B2026-03-16NVIDIA Nemotron 3 Super 120B A12B (Reasoning)2026-03-11NVIDIA Nemotron 3 Super 120B A12B BF162026-03-10NVIDIA Nemotron 3 Nano 4B BF162026-03-07NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)2025-12-15NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning)2025-12-15NVIDIA Nemotron 3 Nano 30B A3B BF162025-12-04NVIDIA Nemotron Parse v1.12025-11-15
Pricing
Input
$0.04
per 1M tokens
Output
$0.16
per 1M tokens
Blended
$0.07
per 1M tokens
Cheaper than 87% of models. Median price is $0.67/1M tokens.
Cost Calculator
Tokens per day1M
100K100M
Daily
$0.07
Monthly
$2.10
vs. Similar Models
NVIDIA Nemotron Nano 9B V2 (Reasoning)
$0.070%
Llama 3 Instruct 8B
$0.070%
Meta: Llama 3.2 1B Instruct
$0.07+1%
Arcee AI: Trinity Mini
$0.07+2%
Performance
Context Window
131K
tokens
Larger than 27% of models
Max Output
16K
tokens
13% of context
Context Window Comparison
DeepSeek: DeepSeek V3.2
131KSame
OpenAI: gpt-oss-120b
131KSame
MoonshotAI: Kimi K2 0711
131KSame
Open Source
other9BGGUF / GPTQ / AWQ
Downloads
863.1K
Likes
497
VRAM (FP16)
16-24 GB
GPU
RTX 4090 / M2 Max