LLM EXPLORER 60,147 MODELS INDEXED

MinerU Popo by DreamEternal

By DreamEternal · 26895 downloads

MinerU Popo is an open-source language model by DreamEternal. Features: 4b LLM, VRAM: 17.6GB, License: mit, Instruction-Based, LLM Explorer Score: 0.31.

Base model:finetune:qwen/qwen3... Base model:qwen/qwen3-vl-4b-in...   En   Instruct   Qwen3 vl   Region:us   Safetensors   Sharded   Tensorflow

MinerU Popo Parameters and Internals

LLM NameMinerU Popo
Repository πŸ€—https://huggingface.co/DreamEternal/MinerU-Popo 
Base Model(s)  Qwen3 VL 4B Instruct   Qwen/Qwen3-VL-4B-Instruct
Model Size4b
Required VRAM17.6 GB
Updated2026-08-30
MaintainerDreamEternal
Model Typeqwen3_vl
Instruction-BasedYes
Model Files  4.9 GB: 1-of-4   4.9 GB: 2-of-4   4.9 GB: 3-of-4   2.9 GB: 4-of-4
Supported Languagesen
Model ArchitectureQwen3VLForConditionalGeneration
Licensemit
Model Max Length262144
Transformers Version4.57.1
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Errorsreplace

Best Alternatives to MinerU Popo

Best Alternatives
Context / RAM
Downloads
Likes
Qwen3 VL 4B Instruct0K / 8.9 GB3611570437
Qwen3 VL 4B Instruct FP80K / 6.1 GB30110365
...rallelTubeDecoding Qwen3 VL 4B0K / 8.9 GB772
Qwen3 VL 4B Instruct0K / 8.9 GB1786411
OMEGA 4B SpatialThink 08040K / 8.9 GB161
GELab Zero 4B Preview0K / 8.9 GB235154
ZwZ 4B0K / 9.7 GB15532
Spatial SSRL Qwen3VL 4B0K / 9.7 GB10114
Qwen3 VL 4B Instruct FP80K / 6.1 GB2673
...L 4B Instruct Unsloth Bnb 4bit0K / 4.3 GB25381712
Note: green Score (e.g. "73.2") means that the model is better than DreamEternal/MinerU-Popo.