← Back to all models
N

Nemotron 3 Nano 30B

by NVIDIA
Efficient Free & Open Source 🏆 Ranked #54 of 85
69.0
Overall Score
out of 100
About

NVIDIA's efficient 30B model optimised for NVIDIA hardware, delivering strong performance per watt for production inference. Tuned for speed and cost-effectiveness on NVIDIA infrastructure.

Key Metrics
Context Window
128K
tokens
Avg Response
680
milliseconds
Input Cost
$0.14
per million tokens
Output Cost
$0.42
per million tokens
Arena ELO
1210
Chatbot Arena rating
MT-Bench
8.5
out of 10
Benchmark Scores
MMLU
78.0%
HumanEval
80.0%
MATH
72.0%
GPQA
40.0%
MT-Bench
85.0/10
Capability Profile
Strengths & Limitations
Strengths
✓ NVIDIA-optimised ✓ Fast inference ✓ Open source ✓ Good reasoning ✓ Efficient on GPU
Limitations
⚠ Best on NVIDIA hardware ⚠ Less general than alternatives ⚠ Newer with limited benchmarks
Ideal Use Cases
NVIDIA deployments Enterprise AI Research Chatbots Code assistance
Model Details
Provider NVIDIA
Released 2025-04-01
Type Free & Open Source
Multimodal No
Tier Efficient
Global rank #54 / 85
Pricing (USD)
Input tokens $0.14/M
Output tokens $0.42/M
Per 1,000 tokens ≈ $0.0001 input / $0.0004 output
All Benchmarks
MMLU 78.0%
HumanEval 80.0%
MATH 72.0%
GPQA 40.0%
MT-Bench 8.5/10
Arena ELO 1210
Compare this model View Rankings

You might also consider