What are the hardware requirements for Invoice Split 2022?

Invoice Split 2022 requires approximately 17.5 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Invoice Split 2022 and how large is it?

Invoice Split 2022 is developed by lugman-madhiai, a model with 8b 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 Invoice Split 2022?

Invoice Split 2022 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Invoice Split 2022 by lugman-madhiai — VRAM 17.5GB

Name: Invoice Split 2022
Author: lugman-madhiai

Invoice Split 2022 is an open-source language model by lugman-madhiai. Features: 8b LLM, VRAM: 17.5GB, License: apache-2.0, Instruction-Based, LLM Explorer Score: 0.27.

Base model:finetune:unsloth/qw... Base model:unsloth/qwen3-vl-8b... Conversational En Endpoints compatible Image-text-to-text Instruct Qwen3 vl Region:us Safetensors Sharded Tensorflow Unsloth

Model Card on HF 🤗: https://huggingface.co/lugman-madhiai/invoice-split-2022

Invoice Split 2022 Parameters and Internals

LLM Name	Invoice Split 2022
Repository 🤗	https://huggingface.co/lugman-madhiai/invoice-split-2022
Base Model(s)	Qwen3 VL 8B Instruct unsloth/Qwen3-VL-8B-Instruct
Model Size	8b
Required VRAM	17.5 GB
Updated	2026-09-27
Maintainer	lugman-madhiai
Model Type	qwen3_vl
Instruction-Based	Yes
Model Files	4.9 GB: 1-of-4 4.9 GB: 2-of-4 5.0 GB: 3-of-4 2.7 GB: 4-of-4
Supported Languages	en
Model Architecture	Qwen3VLForConditionalGeneration
License	apache-2.0
Model Max Length	262144
Tokenizer Class	Qwen2Tokenizer
Padding Token	<\|vision_pad\|>
Errors	replace

Rank the Invoice Split 2022 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 Invoice Split 2022

Best Alternatives	Context / RAM	Downloads	Likes
Qwen3 VL 8B Instruct	0K / 17.5 GB	4494329	1037
PhysBrain1.5 8B	0K / 17.8 GB	638	27
Qwen3 VL 8B Instruct FP8	0K / 10.6 GB	3108604	77
Qwen3vl Resume Parser	0K / 17.5 GB	257455	3
Qwen3 VL 8B Heretic 1.3.0	0K / 17.5 GB	4653	12
ArmorOCR	0K / 17.5 GB	195	9
Qwen3 VL 8B VQA SFT	0K / 17.5 GB	199	0
GUI Owl 1.5 8B Instruct	0K / 17.5 GB	4882	13
ZwZ 8B	0K / 17.6 GB	2586	48
InSight Doc 8B	0K / 17.6 GB	90	3

Note: green Score (e.g. "73.2") means that the model is better than lugman-madhiai/invoice-split-2022.