What are the hardware requirements for Nemotron 3.5 Super VL 120B A12B JANG 4M?

Nemotron 3.5 Super VL 120B A12B JANG 4M requires approximately 75.2 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 Nemotron 3.5 Super VL 120B A12B JANG 4M and how large is it?

Nemotron 3.5 Super VL 120B A12B JANG 4M is developed by OsaurusAI, a model with 120b 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 Super VL 120B A12B JANG 4M?

Nemotron 3.5 Super VL 120B A12B 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 Super VL 120B A12B JANG 4M by OsaurusAI — VRAM 75.2GB, 1024K context

Name: Nemotron 3.5 Super VL 120B A12B JANG 4M
Author: OsaurusAI

Nemotron 3.5 Super VL 120B A12B JANG 4M is an open-source language model by OsaurusAI. Features: 120b LLM, VRAM: 75.2GB, Context: 1024K, License: other, LLM Explorer Score: 0.31.

Agent Apple-silicon Base model:nvidia/nvidia-nemot... Base model:quantized:nvidia/nv... Conversational De En Es Fr Image-text-to-text It Ja Jang Latent-moe Mamba Mlx Moe Mtp Nemotron Nemotron-3.5 Nemotron h Quantized Reasoning Region:us Safetensors Sharded Tensorflow Thinking Tool-use Vision

Model Card on HF 🤗: https://huggingface.co/OsaurusAI/Nemotron-3.5-Super-VL-120B-A12B-JANG_4M

Nemotron 3.5 Super VL 120B A12B JANG 4M Parameters and Internals

LLM Name	Nemotron 3.5 Super VL 120B A12B JANG 4M
Repository 🤗	https://huggingface.co/OsaurusAI/Nemotron-3.5-Super-VL-120B-A12B-JANG_4M
Base Model(s)	nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16 nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16
Model Size	120b
Required VRAM	75.2 GB
Updated	2026-10-21
Maintainer	OsaurusAI
Model Type	nemotron_h
Model Files	4.3 GB: 1-of-16 4.9 GB: 2-of-16 4.8 GB: 3-of-16 4.8 GB: 4-of-16 4.8 GB: 5-of-16 4.8 GB: 6-of-16 4.8 GB: 7-of-16 4.8 GB: 8-of-16 4.8 GB: 9-of-16 4.8 GB: 10-of-16 4.8 GB: 11-of-16 4.8 GB: 12-of-16 4.8 GB: 13-of-16 4.8 GB: 14-of-16 4.8 GB: 15-of-16 3.6 GB: 16-of-16
Supported Languages	en es fr de it ja
Model Architecture	NemotronHForCausalLM
License	other
Context Length	1048576
Model Max Length	1048576
Tokenizer Class	TokenizersBackend
Padding Token	<\|im_end\|>
Vocabulary Size	131072

Rank the Nemotron 3.5 Super VL 120B A12B 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 Super VL 120B A12B JANG 4M

Best Alternatives	Context / RAM	Downloads	Likes
... Nemotron 3.5 Super VL Finance	1024K / 172 GB	2062	11
...motron 3.5 Super VL Healthcare	1024K / 172 GB	2011	10
Phonellm Max Alpha 2	1024K / 188.5 GB	692	4
...on 3 Super 120B A12B Base BF16	1024K / 209.5 GB	13053	32
...motron 3 Super 120B A12B NVFP4	256K / 80.3 GB	3041935	408
...motron 3 Super 120B A12B NVFP4	256K / 80.3 GB	1132	27
...emotron 3 Super 120B A12B BF16	256K / 194.6 GB	864394	414
...DIA Nemotron 3 Super 120B A12B	256K / 214.5 GB	294	3
...Nemotron 3 Super 120B A12B FP8	256K / 128.4 GB	81	10
...Nemotron 3 Super 120B A12B FP8	256K / 128.4 GB	221272	269

Note: green Score (e.g. "73.2") means that the model is better than OsaurusAI/Nemotron-3.5-Super-VL-120B-A12B-JANG_4M.