LLM EXPLORER 62,589 MODELS INDEXED

NVIDIA Nemotron Labs 3 Puzzle 75B A9B FP8 by nvidia

By nvidia · 23607 downloads
HF Repo ↗ Copy URL

NVIDIA Nemotron Labs 3 Puzzle 75B A9B FP8 is an open-source language model by nvidia. Features: 120b LLM, VRAM: 77.1GB, Context: 256K, License: other, LLM Explorer Score: 0.32.

  Arxiv:2411.19146   Arxiv:2512.20848   Arxiv:2604.12374   Arxiv:2607.04371 Base model:nvidia/nvidia-nemot... Base model:quantized:nvidia/nv...   Conversational   Custom code Dataset:nvidia/nemotron-post-t... Dataset:nvidia/nemotron-pre-tr...   De   En   Es   Fr   It   Ja   Latent-moe   Modelopt   Mtp   Nemotron-3   Nemotron h puzzle   Nvidia   Pytorch   Region:us   Safetensors   Sharded   Tensorflow   Zh
Model Card on HF 🤗: https://huggingface.co/nvidia/NVIDIA-Nemotron-Labs-3-Puzzle-75B-A9B-FP8 

NVIDIA Nemotron Labs 3 Puzzle 75B A9B FP8 Parameters and Internals

LLM NameNVIDIA Nemotron Labs 3 Puzzle 75B A9B FP8
Repository 🤗https://huggingface.co/nvidia/NVIDIA-Nemotron-Labs-3-Puzzle-75B-A9B-FP8 
Base Model(s)  ...emotron 3 Super 120B A12B BF16   nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16
Model Size120b
Required VRAM77.1 GB
Updated2026-08-05
Maintainernvidia
Model Typenemotron_h_puzzle
Model Files  10.0 GB: 1-of-8   10.0 GB: 2-of-8   10.0 GB: 3-of-8   10.0 GB: 4-of-8   10.0 GB: 5-of-8   10.0 GB: 6-of-8   10.0 GB: 7-of-8   7.1 GB: 8-of-8   5.9 GB
Supported Languagesen fr es it de ja zh
Model ArchitectureNemotronHPuzzleForCausalLM
Licenseother
Context Length262144
Model Max Length262144
Transformers Version4.45.0
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<|im_end|>
Vocabulary Size131072

Best Alternatives to NVIDIA Nemotron Labs 3 Puzzle 75B A9B FP8

Best Alternatives
Context / RAM
Downloads
Likes
...on Labs 3 Puzzle 75B A9B NVFP4256K / 47.6 GB164224128
...ron Labs 3 Puzzle 75B A9B BF16256K / 150.8 GB272759
Note: green Score (e.g. "73.2") means that the model is better than nvidia/NVIDIA-Nemotron-Labs-3-Puzzle-75B-A9B-FP8.