Nemotron 3.5 Lightning 30B A3B
Active Parameters
30B
Context Length
262K
Modality
Text
Architecture
Mixture of Experts (MoE)
License
other
Release Date
1 Aug 2026
Knowledge Cutoff
-
API Pricing (per 1M)
Input: $0.08 · Output: $0.20
System Requirements
VRAM requirements for different quantization methods and context sizes
1,024 tokens
Consumer
3x RTX 4090
24GB VRAM
Datacenter
1x NVIDIA A100
80GB VRAM
Apple Silicon
1x Apple M3 Max
128GB VRAM
262,144 tokens
Consumer
4x RTX 4090
24GB VRAM
Datacenter
1x NVIDIA A100
80GB VRAM
Apple Silicon
1x Apple M3 Max
128GB VRAM
Architecture Diagram
Evaluation Benchmarks
Rank
#126
| Benchmark | Score | Rank |
|---|---|---|
General Text | 1351 | 132 |
Rankings
Overall Rank
#126
Coding Rank
-
About Nemotron 3.5 Lightning 30B A3B
Nemotron 3.5 Lightning is an open mixture-of-experts model from NVIDIA activating 3B parameters out of 30B total. It is optimized for high-throughput agentic workflows and efficient long-context reasoning.
Technical Specifications
Attention
Attention Structure
Grouped-Query Attention
Attention Heads
32
Key-Value Heads
2
Attention Head Dimension
128
Position Embedding
ROPE
RoPE Theta
10,000
Sliding Window Attention
No
Sliding Window Size
-
Sliding Window Ratio
-
Linear Attention
Yes
Linear Attention Ratio
46.2%
Normalization
RMS Normalization
Activation Function
ReLU2
Dimensions
Hidden Dimension Size
2,688
Number of Layers
52
FFN Intermediate Size (Dense)
1,856
Multi-Token Prediction Heads
1
Tokenizer
Vocabulary Size
131,072
Mixture of Experts
Total Expert Parameters
3.0B
Number of Experts
128
Active Experts
6
Shared Experts
1
FFN Intermediate Size (per Expert)
1,856
Dense Layers Before MoE
-
Resources
About Nemotron 3.5
NVIDIA's Nemotron 3.5 family of open models delivers leading efficiency and accuracy for agentic AI applications. Built on an advanced hybrid Mamba-2 SSM and sparse Mixture-of-Experts architecture with native Multi-Token Prediction (MTP) and speculative decoding harnesses, Nemotron 3.5 models are purpose-built for the high-volume execution layer of always-on agents.