LLM EXPLORER 60,519 MODELS INDEXED

Nemotron 3 Nano Omni 30B A3B Reasoning 4bit by mlx-community

By mlx-community · 332 downloads
HF Repo ↗ Copy URL

Nemotron 3 Nano Omni 30B A3B Reasoning 4bit is an open-source language model by mlx-community. Features: 30b LLM, VRAM: 19.6GB, License: other, Quantized, LLM Explorer Score: 0.25.

  4-bit   4bit Base model:nvidia/nemotron-3-n... Base model:quantized:nvidia/ne...   Conversational Dataset:nvidia/nemotron-image-...   Image-text-to-text   Mlx   Multimodal Nemotronh nano omni reasoning ...   Nvidia   Pytorch   Quantized   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/mlx-community/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-4bit 

Nemotron 3 Nano Omni 30B A3B Reasoning 4bit Parameters and Internals

LLM NameNemotron 3 Nano Omni 30B A3B Reasoning 4bit
Repository 🤗https://huggingface.co/mlx-community/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-4bit 
Base Model(s)  ...no Omni 30B A3B Reasoning BF16   nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16
Model Size30b
Required VRAM19.6 GB
Updated2026-08-08
Maintainermlx-community
Model TypeNemotronH_Nano_Omni_Reasoning_V3
Model Files  5.1 GB: 1-of-4   5.3 GB: 2-of-4   5.3 GB: 3-of-4   3.9 GB: 4-of-4
Quantization Type4bit
Model ArchitectureNemotronH_Nano_Omni_Reasoning_V3
Licenseother
Model Max Length262144
Tokenizer ClassTokenizersBackend
Padding Token<|im_end|>

Best Alternatives to Nemotron 3 Nano Omni 30B A3B Reasoning 4bit

Best Alternatives
Context / RAM
Downloads
Likes
...no Omni 30B A3B Reasoning 8bit0K / 35.7 GB1651
...no Omni 30B A3B Reasoning BF160K / 66.1 GB447327407
...A3B Reasoning Abliterated BF160K / 66.1 GB170
... 3 Nano Omni 30B A3B Reasoning0K / 66.1 GB50216
...no Omni 30B A3B Reasoning Bf160K / 65.8 GB1261
...o Omni 30B A3B Reasoning Mxfp80K / 34.8 GB1241
Note: green Score (e.g. "73.2") means that the model is better than mlx-community/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-4bit.