LLM EXPLORER 67,390 MODELS INDEXED

NVIDIA Nemotron 3.5 Super VL 120B A12B NVFP4 Global Pruned 40 by nota-ai

By nota-ai · 46 downloads
HF Repo ↗ Copy URL

NVIDIA Nemotron 3.5 Super VL 120B A12B NVFP4 Global Pruned 40 is an open-source language model by nota-ai. Features: 120b LLM, VRAM: 21.8GB, License: other, LLM Explorer Score: 0.33.

  8-bit Base model:nvidia/nvidia-nemot... Base model:quantized:nvidia/nv...   Conversational   Custom code   Endpoints compatible   Expert-pruning   Image-text-to-text   Modelopt mixed   Moe   Nemotron h omni   Nvfp4   Pruning   Region:us   Safetensors   Sharded   Tensorflow   Vllm
Model Card on HF 🤗: https://huggingface.co/nota-ai/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-NVFP4-Global-Pruned-40 

NVIDIA Nemotron 3.5 Super VL 120B A12B NVFP4 Global Pruned 40 Parameters and Internals

LLM NameNVIDIA Nemotron 3.5 Super VL 120B A12B NVFP4 Global Pruned 40
Repository 🤗https://huggingface.co/nota-ai/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-NVFP4-Global-Pruned-40 
Base Model(s)  nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-NVFP4   nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-NVFP4
Model Size120b
Required VRAM21.8 GB
Updated2026-11-13
Maintainernota-ai
Model Typenemotron_h_omni
Model Files  2.9 GB: 1-of-88   1.6 GB: 2-of-88   0.1 GB: 3-of-88   1.6 GB: 4-of-88   0.1 GB: 5-of-88   1.0 GB: 6-of-88   0.1 GB: 7-of-88   0.0 GB: 8-of-88   0.9 GB: 9-of-88   0.1 GB: 10-of-88   0.9 GB: 11-of-88   0.1 GB: 12-of-88   0.9 GB: 13-of-88   0.1 GB: 14-of-88   0.9 GB: 15-of-88   0.1 GB: 16-of-88   0.0 GB: 17-of-88   0.9 GB: 18-of-88   0.1 GB: 19-of-88   0.9 GB: 20-of-88   0.1 GB: 21-of-88   0.9 GB: 22-of-88   0.1 GB: 23-of-88   0.9 GB: 24-of-88   0.1 GB: 25-of-88   0.0 GB: 26-of-88   0.9 GB: 27-of-88   0.1 GB: 28-of-88   1.0 GB: 29-of-88   0.1 GB: 30-of-88   0.9 GB: 31-of-88   0.1 GB: 32-of-88   1.0 GB: 33-of-88   0.1 GB: 34-of-88   1.0 GB: 35-of-88   0.1 GB: 36-of-88   0.0 GB: 37-of-88   1.0 GB: 38-of-88   0.1 GB: 39-of-88
Model ArchitectureNemotronH_Omni_Reasoning_V3
Licenseother
Transformers Version5.8.1

Best Alternatives to NVIDIA Nemotron 3.5 Super VL 120B A12B NVFP4 Global Pruned 40

Best Alternatives
Context / RAM
Downloads
Likes
...n 3.5 Super VL 120B A12B NVFP40K / 30 GB9322169
...on 3.5 Super VL 120B A12B BF160K / 148 GB1509578
...5 Super VL 120B A12B Base BF160K / 144 GB103051
...Nemotron 3.5 Bolt 74B A9B BF160K / 82.8 GB219340
...0B A12B NVFP4 Global Pruned 200K / 27.1 GB477
...n 3.5 Super VL 120B A12B NVFP40K / 31.7 GB12563
...emotron 3.5 Super VL 120B A12B0K / 160 GB4065
...n 3.5 Super VL 120B A12B NVFP40K / 78.6 GB4481
....5 Super VL 120B A12B EXL3 2.00K / 36.6 GB2641
....5 Super VL 120B A12B EXL3 4.00K / 64.7 GB2631
Note: green Score (e.g. "73.2") means that the model is better than nota-ai/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-NVFP4-Global-Pruned-40.