LLM EXPLORER 58,133 MODELS INDEXED

NVIDIA Nemotron 3 Nano 30B A3B MLX 6Bit by mlx-community

By mlx-community · 148 downloads
HF Repo ↗ Copy URL

NVIDIA Nemotron 3 Nano 30B A3B MLX 6Bit is an open-source language model by mlx-community. Features: 30b LLM, VRAM: 25.8GB, Context: 256K, License: other, Quantized, Instruction-Based, LLM Explorer Score: 0.35, ELO: 1317.

  6bit Base model:finetune:nvidia/nvi... Base model:nvidia/nvidia-nemot...   Conversational Dataset:nvidia/nemotron-3-nano... Dataset:nvidia/nemotron-agenti... Dataset:nvidia/nemotron-cc-cod... Dataset:nvidia/nemotron-cc-mat...   Dataset:nvidia/nemotron-cc-v2 Dataset:nvidia/nemotron-cc-v2.... Dataset:nvidia/nemotron-compet... Dataset:nvidia/nemotron-instru... Dataset:nvidia/nemotron-math-p... Dataset:nvidia/nemotron-math-v... Dataset:nvidia/nemotron-pretra... Dataset:nvidia/nemotron-pretra... Dataset:nvidia/nemotron-pretra... Dataset:nvidia/nemotron-pretra... Dataset:nvidia/nemotron-pretra... Dataset:nvidia/nemotron-scienc...   De   En   Es   Fr   Instruct   It   Ja   Mlx   Nvidia   Pytorch   Quantized   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/mlx-community/NVIDIA-Nemotron-3-Nano-30B-A3B-MLX-6Bit 

NVIDIA Nemotron 3 Nano 30B A3B MLX 6Bit Benchmarks

LMSys ELO 1317 vs 1272 (so35) 3.5%
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

NVIDIA Nemotron 3 Nano 30B A3B MLX 6Bit Parameters and Internals

LLM NameNVIDIA Nemotron 3 Nano 30B A3B MLX 6Bit
Repository 🤗https://huggingface.co/mlx-community/NVIDIA-Nemotron-3-Nano-30B-A3B-MLX-6Bit 
Base Model(s)  ...A Nemotron 3 Nano 30B A3B BF16   nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16
Model Size30b
Required VRAM25.8 GB
Updated2026-08-05
Maintainermlx-community
Model Typenemotron_h
Instruction-BasedYes
Model Files  5.2 GB: 1-of-5   5.0 GB: 2-of-5   5.4 GB: 3-of-5   5.0 GB: 4-of-5   5.2 GB: 5-of-5
Supported Languagesen es fr de ja it
Quantization Type6bit
Model ArchitectureNemotronHForCausalLM
Licenseother
Context Length262144
Model Max Length262144
Transformers Version4.55.4
Tokenizer ClassTokenizersBackend
Vocabulary Size131072
Torch Data Typebfloat16

Best Alternatives to NVIDIA Nemotron 3 Nano 30B A3B MLX 6Bit

Best Alternatives
Context / RAM
Downloads
Likes
...motron 3 Nano 30B A3B MLX 4Bit256K / 17.8 GB2051
...tron 3 Nano 30B A3B OptiQ 4bit256K / 22.1 GB6442
...A Nemotron 3 Nano 30B A3B 4bit256K / 17.8 GB7284
...motron 3 Nano 30B A3B MLX 8Bit256K / 33.5 GB2392
...A Nemotron 3 Nano 30B A3B BF16256K / 63.2 GB1645889752
... Nemotron 3 Nano 30B A3B NVFP4256K / 19.3 GB15688
...IA Nemotron 3 Nano 30B A3B FP8256K / 32.7 GB566152356
... Nemotron 3 Nano 30B A3B NVFP4256K / 19.3 GB765499174
Nemotron 3 Nano 30B A3B256K / 63.2 GB17431514
... Nemotron 3 Nano 30B A3B NVFP4256K / 19.3 GB200215
Note: green Score (e.g. "73.2") means that the model is better than mlx-community/NVIDIA-Nemotron-3-Nano-30B-A3B-MLX-6Bit.