LLM EXPLORER 63,791 MODELS INDEXED

Nemotron Parse 2.0 8bit by mlx-community

By mlx-community · 123 downloads
HF Repo ↗ Copy URL

Nemotron Parse 2.0 8bit is an open-source language model by mlx-community. Features: 750.1m LLM, VRAM: 1.7GB, License: apache-2.0, Quantized, LLM Explorer Score: 0.26.

  8-bit   8bit Base model:nvidia/nvidia-nemot... Base model:quantized:nvidia/nv...   Custom code   Document-parsing   Image-text-to-text   Mlx   Multimodal   Nemotron parse   Ocr   Quantized   Region:us   Safetensors   Vision   Vision-encoder-decoder
Model Card on HF 🤗: https://huggingface.co/mlx-community/Nemotron-Parse-2.0-8bit 

Nemotron Parse 2.0 8bit Parameters and Internals

LLM NameNemotron Parse 2.0 8bit
Repository 🤗https://huggingface.co/mlx-community/Nemotron-Parse-2.0-8bit 
Base Model(s)  nvidia/NVIDIA-Nemotron-Parse-2.0   nvidia/NVIDIA-Nemotron-Parse-2.0
Model Size750.1m
Required VRAM1.7 GB
Updated2026-08-24
Maintainermlx-community
Model Typenemotron_parse
Model Files  1.7 GB
Quantization Type8bit
Model ArchitectureNemotronParseForConditionalGeneration
Licenseapache-2.0
Model Max Length9000
Transformers Version5.6.1
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<pad>
Vocabulary Size72256