Llama 3.1 Nemotron Nano 8B V1
Llama 3.1 Nemotron Nano 8B v1 is a compact language model by NVIDIA, based on the Llama 3.1 architecture with Nemotron enhancements. With 8 billion parameters, it offers strong performance for its size class in reasoning, coding, and general tasks, suitable for efficient deployment.
Key Specifications
Parameters
8.0B
Context
-
Release Date
March 18, 2025
Average Score
72.2%
Timeline
Key dates in the model's history
Announcement
March 18, 2025
Last Update
July 19, 2025
Today
March 25, 2026
Technical Specifications
Parameters
8.0B
Training Tokens
-
Knowledge Cutoff
December 31, 2023
Family
-
Capabilities
MultimodalZeroEval
Benchmark Results
Model performance metrics across various tests and benchmarks
Programming
Programming skills tests
MBPP
0-shot, Pass@1, "" • Self-reported
Reasoning
Logical reasoning and analysis
GPQA
Diamond, Pass@1, Diamond GSM8K, MATH Diamond: - accuracy - GPT-4 Claude • Self-reported
Other Tests
Specialized benchmarks
AIME 2025
Pass@1, Pass@1 — Pass@k (Pass@100), Pass@1 Pass@1 "" : 1. 2. 3. 4. : - "" : - • Self-reported
BFCL v2
Score, Reasoning AI: Score • Self-reported
IFEval
# Strict Accuracy, Reasoning "/", : : - "Correct ": "": ## ### 8 5 ? ### = 8 × 5 = 40 ². ### Score - Correct ? ✓ - ? ✓ - evaluation: • Self-reported
MATH-500
Pass@1, AI: • Self-reported
MT-Bench
Score, Reasoning AI: Score • Self-reported
License & Metadata
License
llama_3_1_community_license
Announcement Date
March 18, 2025
Last Updated
July 19, 2025
Similar Models
All Models
Phi 4 Mini Reasoning
Microsoft
3.8B
Best score:0.5 (GPQA)
Released:Apr 2025
DeepSeek R1 Distill Qwen 7B
DeepSeek
7.6B
Best score:0.5 (GPQA)
Released:Jan 2025
Phi 4 Mini
Microsoft
3.8B
Best score:0.8 (ARC)
Released:Feb 2025
Gemma 2 9B
9.2B
Best score:0.7 (MMLU)
Released:Jun 2024
DeepSeek R1 Distill Llama 8B
DeepSeek
8.0B
Best score:0.5 (GPQA)
Released:Jan 2025
Ministral 8B Instruct
Mistral AI
8.0B
Best score:0.7 (ARC)
Released:Oct 2024
Price:$0.10/1M tokens
Llama 3.2 3B Instruct
Meta
3.2B
Best score:0.8 (ARC)
Released:Sep 2024
Price:$0.01/1M tokens
Qwen2 7B Instruct
Alibaba
7.6B
Best score:0.8 (HumanEval)
Released:Jul 2024
Recommendations are based on similarity of characteristics: developer organization, multimodality, parameter size, and benchmark performance. Choose a model to compare or go to the full catalog to browse all available AI models.