What are the hardware requirements for NuExtract 2 2B?

NuExtract 2 2B requires approximately 4.4 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed NuExtract 2 2B and how large is it?

NuExtract 2 2B is developed by numind, a model with 2b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

Where can I download or evaluate NuExtract 2 2B?

NuExtract 2 2B is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

NuExtract 2 2B by numind — VRAM 4.4GB

Name: NuExtract 2 2B
Author: numind

NuExtract 2 2B is an open-source language model by numind. Features: 2b LLM, VRAM: 4.4GB, License: mit, LLM Explorer Score: 0.18.

Base model:finetune:opengvlab/... Base model:opengvlab/internvl2... Conversational Custom code Internvl chat Multilingual Region:us Safetensors

Model Card on HF 🤗: https://huggingface.co/numind/NuExtract-2-2B

NuExtract 2 2B Parameters and Internals

LLM Name	NuExtract 2 2B
Repository 🤗	https://huggingface.co/numind/NuExtract-2-2B
Base Model(s)	InternVL2 5 2B OpenGVLab/InternVL2_5-2B
Model Size	2b
Required VRAM	4.4 GB
Updated	2025-04-15
Maintainer	numind
Model Type	internvl_chat
Model Files	4.4 GB
Model Architecture	InternVLChatModel
License	mit
Model Max Length	8192
Tokenizer Class	InternLM2Tokenizer
Padding Token	</s>
Torch Data Type	bfloat16

Rank the NuExtract 2 2B capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

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

Best Alternatives to NuExtract 2 2B

Best Alternatives	Context / RAM	Downloads	Likes
InternVL3 5 2B	0K / 4.7 GB	7876	20
InternVL3 2B	0K / 4.2 GB	37301	46
InternVL3 5 2B Instruct	0K / 4.7 GB	7296	4
InternVL3 5 2B Flash	0K / 5 GB	486	6
InternVL3 5 2B MPO	0K / 4.7 GB	71	5
InternVL3 5 2B Pretrained	0K / 4.7 GB	40	3
Docopilot 2B	0K / 4.4 GB	21	8
InternVL3 2B Instruct	0K / 4.2 GB	900	7
InternVL3 2B	0K / 4.2 GB	19	2
InternVL3 2B Pretrained	0K / 4.2 GB	42	1

Note: green Score (e.g. "73.2") means that the model is better than numind/NuExtract-2-2B.