What are the hardware requirements for Nemotron 3.5 Lightning 30B A3B JANG 4M?

Nemotron 3.5 Lightning 30B A3B JANG 4M requires approximately 19.8 GB of VRAM and supports a context window of 256K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Nemotron 3.5 Lightning 30B A3B JANG 4M and how large is it?

Nemotron 3.5 Lightning 30B A3B JANG 4M is developed by OsaurusAI, a model with 30b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

Where can I download or evaluate Nemotron 3.5 Lightning 30B A3B JANG 4M?

Nemotron 3.5 Lightning 30B A3B JANG 4M is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Nemotron 3.5 Lightning 30B A3B JANG 4M by OsaurusAI — VRAM 19.8GB, 256K context

Name: Nemotron 3.5 Lightning 30B A3B JANG 4M
Author: OsaurusAI

Nemotron 3.5 Lightning 30B A3B JANG 4M is an open-source language model by OsaurusAI. Features: 30b LLM, VRAM: 19.8GB, Context: 256K, License: other, LLM Explorer Score: 0.28.

Base model:nvidia/nvidia-nemot... Base model:quantized:nvidia/nv... Conversational De En Es Fr Hybrid It Ja Jang Mamba2 Mlx Moe Nemotron Nemotron-3.5 Nemotron h Osaurus Region:us Safetensors Sharded Tensorflow Vmlx-swift

Model Card on HF 🤗: https://huggingface.co/OsaurusAI/Nemotron-3.5-Lightning-30B-A3B-JANG_4M

Nemotron 3.5 Lightning 30B A3B JANG 4M Parameters and Internals

LLM Name	Nemotron 3.5 Lightning 30B A3B JANG 4M
Repository 🤗	https://huggingface.co/OsaurusAI/Nemotron-3.5-Lightning-30B-A3B-JANG_4M
Base Model(s)	nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16 nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16
Model Size	30b
Required VRAM	19.8 GB
Updated	2026-08-13
Maintainer	OsaurusAI
Model Type	nemotron_h
Model Files	0.6 GB: 1-of-26 0.8 GB: 2-of-26 0.8 GB: 3-of-26 0.8 GB: 4-of-26 0.8 GB: 5-of-26 0.8 GB: 6-of-26 0.8 GB: 7-of-26 0.8 GB: 8-of-26 0.8 GB: 9-of-26 0.8 GB: 10-of-26 0.8 GB: 11-of-26 0.8 GB: 12-of-26 0.8 GB: 13-of-26 0.8 GB: 14-of-26 0.8 GB: 15-of-26 0.8 GB: 16-of-26 0.8 GB: 17-of-26 0.8 GB: 18-of-26 0.8 GB: 19-of-26 0.8 GB: 20-of-26 0.8 GB: 21-of-26 0.8 GB: 22-of-26 0.8 GB: 23-of-26 0.8 GB: 24-of-26 0.8 GB: 25-of-26 0.0 GB: 26-of-26
Supported Languages	en es fr de it ja
Model Architecture	NemotronHForCausalLM
License	other
Context Length	262144
Model Max Length	262144
Transformers Version	4.57.6
Tokenizer Class	PreTrainedTokenizerFast
Padding Token	<\|im_end\|>
Vocabulary Size	131072

Rank the Nemotron 3.5 Lightning 30B A3B JANG 4M 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 Nemotron 3.5 Lightning 30B A3B JANG 4M

Best Alternatives	Context / RAM	Downloads	Likes
...on 3.5 Lightning 30B A3B NVFP4	1024K / 12.6 GB	19250	100
...A Nemotron 3 Nano 30B A3B BF16	256K / 63.2 GB	1645889	752
...ron 3.5 Lightning 30B A3B BF16	256K / 65.9 GB	15740	62
... Nemotron 3 Nano 30B A3B NVFP4	256K / 19.3 GB	1568	8
Nemotron Cascade 2 30B A3B	256K / 63.2 GB	88240	518
...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
...tron 3.5 30B A3B Antislop FTPO	256K / 65.9 GB	201	4
....5 Lightning 30B A3B Base BF16	256K / 65.9 GB	336	12
...on 3.5 Lightning 30B A3B Mxfp4	256K / 16.8 GB	308	2

Note: green Score (e.g. "73.2") means that the model is better than OsaurusAI/Nemotron-3.5-Lightning-30B-A3B-JANG_4M.