Nemotron 3.5 Lightning
Active Parameters
30B
Context Length
1M
Modality
Text
Architecture
Mixture of Experts (MoE)
License
OpenMDW-1.1
Release Date
11 Aug 2026
Knowledge Cutoff
-
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
1,000,000 tokens
Consumer
15x RTX 4090
24GB VRAM
Datacenter
4x NVIDIA A100
80GB VRAM
Apple Silicon
3x Apple M3 Max
128GB VRAM
Architecture Diagram
Evaluation Benchmarks
No evaluation benchmarks for Nemotron 3.5 Lightning available.
Rankings
Overall Rank
-
Coding Rank
-
About Nemotron 3.5 Lightning
NVIDIA Nemotron 3.5 Lightning is an open-weight hybrid reasoning Mixture-of-Experts (MoE) foundation model with 30 billion total parameters and roughly 3 billion active parameters per token. Built on a 52-layer hybrid backbone interleaving Mamba-2 State Space Model (SSM) blocks with sparse MoE layers (128 routed experts, top-6 active + 1 shared expert) and select attention layers, it is engineered as a high-speed execution workhorse for long-running agent workflows, tool calls, and subagent delegation with up to 1M context.
Technical Specifications
Attention
Attention Structure
Multi-Head Attention
Attention Heads
64
Key-Value Heads
-
Attention Head Dimension
128
Position Embedding
ROPE
RoPE Theta
-
Sliding Window Attention
No
Sliding Window Size
-
Sliding Window Ratio
-
Linear Attention
Yes
Linear Attention Ratio
-
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
7
Shared Experts
1
FFN Intermediate Size (per Expert)
1,856
Dense Layers Before MoE
-
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.
Other Nemotron 3.5 Models
- No related models available