LLM EXPLORER
 LLM Explorer: A Curated Large Language Model Directory and Analytics
Dark Theme
  Agents   Benchmarks   LLM  List    LLM Hosting    LLM Leaderboards    Blog    Newsfeed    Advertise

Nemotron 3 Super 120B A12B MLX 6bit by mlx-community

 »  All LLMs  »  mlx-community  »  Nemotron 3 Super 120B A12B MLX 6bit   URL Share it on

  328   

Nemotron 3 Super 120B A12B MLX 6bit is an open-source language model by mlx-community. Features: 120b LLM, VRAM: 97.7GB, Context: 256K, License: other, Quantized, LLM Explorer Score: 0.26.

  6-bit   6bit   Apple-silicon Base model:nvidia/nvidia-nemot... Base model:quantized:nvidia/nv...   Conversational   Custom code   En   Lm-studio   Mamba   Mamba2   Mixture-of-experts   Mlx   Nemotron   Nemotron h   Quantized   Reasoning   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/mlx-community/Nemotron-3-Super-120B-A12B-MLX-6bit 

Nemotron 3 Super 120B A12B MLX 6bit Benchmarks

LLME Score: 0.26046
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Nemotron 3 Super 120B A12B MLX 6bit (mlx-community/Nemotron-3-Super-120B-A12B-MLX-6bit)
🌟 Advertise your project 🚀

Nemotron 3 Super 120B A12B MLX 6bit Parameters and Internals

LLM NameNemotron 3 Super 120B A12B MLX 6bit
Repository 🤗https://huggingface.co/mlx-community/Nemotron-3-Super-120B-A12B-MLX-6bit 
Base Model(s)  ...emotron 3 Super 120B A12B BF16   nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16
Model Size120b
Required VRAM97.7 GB
Updated2026-06-16
Maintainermlx-community
Model Typenemotron_h
Model Files  5.3 GB: 1-of-20   4.9 GB: 2-of-20   4.8 GB: 3-of-20   4.9 GB: 4-of-20   4.8 GB: 5-of-20   4.9 GB: 6-of-20   4.8 GB: 7-of-20   4.9 GB: 8-of-20   4.8 GB: 9-of-20   4.8 GB: 10-of-20   4.9 GB: 11-of-20   4.8 GB: 12-of-20   4.9 GB: 13-of-20   4.8 GB: 14-of-20   4.8 GB: 15-of-20   4.9 GB: 16-of-20   4.8 GB: 17-of-20   4.9 GB: 18-of-20   4.8 GB: 19-of-20   5.2 GB: 20-of-20
Supported Languagesen
Quantization Type6bit
Model ArchitectureNemotronHForCausalLM
Licenseother
Context Length262144
Model Max Length262144
Transformers Version4.57.6
Tokenizer ClassTokenizersBackend
Padding Token<|im_end|>
Vocabulary Size131072

Best Alternatives to Nemotron 3 Super 120B A12B MLX 6bit

Best Alternatives
Context / RAM
Downloads
Likes
...n 3 Super 120B A12B OptiQ 2bit256K / 45.6 GB1742
...emotron 3 Super 120B A12B 5bit256K / 83.1 GB28472
...on 3 Super 120B A12B Base BF161024K / 209.5 GB1137530
...emotron 3 Super 120B A12B BF16256K / 194.6 GB780467376
...motron 3 Super 120B A12B NVFP4256K / 80.3 GB1127444315
...Nemotron 3 Super 120B A12B FP8256K / 128.4 GB25789
...Nemotron 3 Super 120B A12B FP8256K / 128.4 GB430121251
...DIA Nemotron 3 Super 120B A12B256K / 214.5 GB11573
... Super 64B A12B Math REAP BF16256K / 128.6 GB18141
...motron 3 Super 120B A12B NVFP4256K / 80.3 GB240027
Note: green Score (e.g. "73.2") means that the model is better than mlx-community/Nemotron-3-Super-120B-A12B-MLX-6bit.

Rank the Nemotron 3 Super 120B A12B MLX 6bit Capabilities

🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟

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  

What open-source LLMs or SLMs are you in search of? 54454 in total.

Email us: info@extractum.io. Our Privacy Policy  | Terms and Conditions  | Suggest an improvement.
Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a
  Support LLM Explorer