What are the hardware requirements for NVIDIA Nemotron 3.5 Lightning 30B A3B NVFP4?

NVIDIA Nemotron 3.5 Lightning 30B A3B NVFP4 requires approximately 12.6 GB of VRAM and supports a context window of 1024K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed NVIDIA Nemotron 3.5 Lightning 30B A3B NVFP4 and how large is it?

NVIDIA Nemotron 3.5 Lightning 30B A3B NVFP4 is developed by nvidia, a model with 30b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does NVIDIA Nemotron 3.5 Lightning 30B A3B NVFP4 perform on standard benchmarks?

NVIDIA Nemotron 3.5 Lightning 30B A3B NVFP4 has the following published scores: LMSYS ELO 1355. Compare against reference models on this page or on the LLM Explorer leaderboards.

NVIDIA Nemotron 3.5 Lightning 30B A3B NVFP4 by nvidia — VRAM 12.6GB, 1024K context

Name: NVIDIA Nemotron 3.5 Lightning 30B A3B NVFP4
Author: nvidia

NVIDIA Nemotron 3.5 Lightning 30B A3B NVFP4 is an open-source language model by nvidia. Features: 30b LLM, VRAM: 12.6GB, Context: 1024K, License: other, LLM Explorer Score: 0.53, ELO: 1355.

8-bit Conversational De Deploy:azure En Endpoints compatible Es Fr It Ja Modelopt Nemotron-3.5 Nemotron h Nvidia Pytorch Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4

NVIDIA Nemotron 3.5 Lightning 30B A3B NVFP4 Benchmarks

LMSys ELO 1355 vs 1272 (so35) 6.5%

^nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

What is the LLM Explorer Rank (Score)

NVIDIA Nemotron 3.5 Lightning 30B A3B NVFP4 Parameters and Internals

LLM Name	NVIDIA Nemotron 3.5 Lightning 30B A3B NVFP4
Repository 🤗	https://huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4
Model Size	30b
Required VRAM	12.6 GB
Updated	2026-08-11
Maintainer	nvidia
Model Type	nemotron_h
Model Files	0.7 GB: 1-of-52 0.7 GB: 2-of-52 0.0 GB: 3-of-52 0.7 GB: 4-of-52 0.0 GB: 5-of-52 0.0 GB: 6-of-52 0.7 GB: 7-of-52 0.0 GB: 8-of-52 0.7 GB: 9-of-52 0.0 GB: 10-of-52 0.7 GB: 11-of-52 0.0 GB: 12-of-52 0.0 GB: 13-of-52 0.7 GB: 14-of-52 0.0 GB: 15-of-52 0.7 GB: 16-of-52 0.0 GB: 17-of-52 0.7 GB: 18-of-52 0.0 GB: 19-of-52 0.0 GB: 20-of-52 0.7 GB: 21-of-52 0.0 GB: 22-of-52 0.7 GB: 23-of-52 0.0 GB: 24-of-52 0.7 GB: 25-of-52 0.0 GB: 26-of-52 0.0 GB: 27-of-52 0.7 GB: 28-of-52 0.0 GB: 29-of-52 0.7 GB: 30-of-52 0.0 GB: 31-of-52 0.7 GB: 32-of-52 0.0 GB: 33-of-52 0.0 GB: 34-of-52 0.7 GB: 35-of-52 0.0 GB: 36-of-52 0.7 GB: 37-of-52 0.0 GB: 38-of-52 0.7 GB: 39-of-52
Supported Languages	en es fr de it ja
Model Architecture	NemotronHForCausalLM
License	other
Context Length	1048576
Model Max Length	1048576
Transformers Version	5.8.1
Vocabulary Size	131072

Rank the NVIDIA Nemotron 3.5 Lightning 30B A3B NVFP4 capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

Instruction Following and Task Automation
Factuality and Completeness of Knowledge
Censorship and Alignment
Data Analysis and Insight Generation
Text Generation
Text Summarization and Feature Extraction
Code Generation
Multi-Language Support and Translation

Best Alternatives to NVIDIA Nemotron 3.5 Lightning 30B A3B NVFP4

Best Alternatives	Context / RAM	Downloads	Likes
...30B A3B NVFP4 Global Pruned 15	1024K / 11 GB	148	19
...A Nemotron 3 Nano 30B A3B BF16	256K / 63.2 GB	1645889	752
... Nemotron 3 Nano 30B A3B NVFP4	256K / 19.3 GB	1568	8
...ron 3.5 Lightning 30B A3B BF16	256K / 65.9 GB	15740	62
Nemotron Cascade 2 30B A3B	256K / 63.2 GB	88240	518
Phonellm Alpha 1	256K / 63.2 GB	64	107
...IA Nemotron 3 Nano 30B A3B FP8	256K / 32.7 GB	566152	356
... Nemotron 3 Nano 30B A3B NVFP4	256K / 19.3 GB	765499	174
...otron 3 Nano 30B A3B Base BF16	256K / 63.2 GB	90736	127
Nemotron 3 Nano 30B A3B	256K / 63.2 GB	174315	14