Open Systems, Blockchain & Business Daily

OSBBD

AI, money and the software behind them.

Nemotron 3.5 Lightning

Nemotron 3.5 Lightning is an open-weight language model from NVIDIA, released on August 11, 2026. It is a mixture-of-experts model with 30B total parameters, of which 3B are active for each token. NVIDIA lists a context window of up to 1M tokens. The model takes text input.

Developer
NVIDIA
Released
August 11, 2026
Total parameters
30B
Active parameters per token
3B
Architecture
MoE
Context window
1M
Input
Text
License
OpenMDW License Agreement v1.1
Commercial use
Yes
Official weights, GB
65.8 GB
Hugging Face repository
huggingface.co
Checked on

The weights are released under the OpenMDW License Agreement v1.1, which allows commercial use.

The official weights on Hugging Face take about 65.8 GB in BF16. Running the model needs at least that much memory across GPUs and system RAM, plus room for the context cache; quantized versions need less.

Total parameters, billions
30B
Active parameters, billions
3B
Context window, tokens
1M
License type
Custom license
License conditions
OpenMDW 1.1: redistributions must include the agreement and origin notices.
Weights precision
BF16
Official quantized or alternative versions
nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4
License text
raw.githubusercontent.com
Sources
PageURL
Hugging Face model cardhttps://huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16/raw/main/README.md
Hugging Face weights indexhttps://huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16/raw/main/model.safetensors.index.json
OSBBD

What are you looking for?

Search by headline, topic or keyword.