What are the hardware requirements for IoU PD?

IoU PD requires approximately 9.7 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed IoU PD and how large is it?

IoU PD is developed by xyzzzh, a model with 4.4b 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 IoU PD?

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

IoU PD by xyzzzh — VRAM 9.7GB

Name: IoU PD
Author: xyzzzh

IoU PD is an open-source language model by xyzzzh. Features: 4.4b LLM, VRAM: 9.7GB, LLM Explorer Score: 0.27.

Arxiv:2607.15732 Conversational Coordinate-generation En Endpoints compatible Image-text-to-text Knowledge-distillation Privileged-information Qwen3 vl Referring-expression-comprehen... Region:us Safetensors Sharded Tensorflow Visual-grounding

Model Card on HF 🤗: https://huggingface.co/xyzzzh/IoU-PD

IoU PD Parameters and Internals

LLM Name	IoU PD
Repository 🤗	https://huggingface.co/xyzzzh/IoU-PD
Model Size	4.4b
Required VRAM	9.7 GB
Updated	2026-09-20
Maintainer	xyzzzh
Model Type	qwen3_vl
Model Files	5.0 GB: 1-of-2 4.7 GB: 2-of-2
Supported Languages	en
Model Architecture	Qwen3VLForConditionalGeneration
Model Max Length	262144
Transformers Version	4.57.1
Tokenizer Class	Qwen2Tokenizer
Padding Token	<\|endoftext\|>
Errors	replace

Rank the IoU PD 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