LLM EXPLORER 57,918 MODELS INDEXED

Qwen2 VL 72B Instruct by unsloth

By unsloth · 61 downloads
HF Repo ↗ Copy URL

Qwen2 VL 72B Instruct is an open-source language model by unsloth. Features: 72b LLM, VRAM: 147.5GB, Context: 32K, License: apache-2.0, Instruction-Based, LLM Explorer Score: 0.15.

  Arxiv:2308.12966   Arxiv:2409.12191 Base model:finetune:qwen/qwen2... Base model:qwen/qwen2-vl-72b-i...   Conversational   En   Endpoints compatible   Image-text-to-text   Instruct   Multimodal   Qwen   Qwen2   Qwen2 vl   Region:us   Safetensors   Sharded   Tensorflow   Unsloth   Vision
Model Card on HF 🤗: https://huggingface.co/unsloth/Qwen2-VL-72B-Instruct 

Qwen2 VL 72B Instruct Parameters and Internals

LLM NameQwen2 VL 72B Instruct
Repository 🤗https://huggingface.co/unsloth/Qwen2-VL-72B-Instruct 
Base Model(s)  Qwen2 VL 72B Instruct   Qwen/Qwen2-VL-72B-Instruct
Model Size72b
Required VRAM147.5 GB
Updated2026-08-10
Maintainerunsloth
Model Typeqwen2_vl
Instruction-BasedYes
Model Files  4.7 GB: 1-of-31   4.8 GB: 2-of-31   5.0 GB: 3-of-31   4.8 GB: 4-of-31   4.8 GB: 5-of-31   4.8 GB: 6-of-31   5.0 GB: 7-of-31   4.8 GB: 8-of-31   4.8 GB: 9-of-31   4.8 GB: 10-of-31   5.0 GB: 11-of-31   4.8 GB: 12-of-31   4.8 GB: 13-of-31   4.8 GB: 14-of-31   5.0 GB: 15-of-31   4.8 GB: 16-of-31   4.8 GB: 17-of-31   4.8 GB: 18-of-31   5.0 GB: 19-of-31   4.8 GB: 20-of-31   4.8 GB: 21-of-31   4.8 GB: 22-of-31   5.0 GB: 23-of-31   4.8 GB: 24-of-31   4.8 GB: 25-of-31   4.8 GB: 26-of-31   5.0 GB: 27-of-31   4.8 GB: 28-of-31   4.8 GB: 29-of-31   4.5 GB: 30-of-31   2.5 GB: 31-of-31
Supported Languagesen
Model ArchitectureQwen2VLForConditionalGeneration
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.49.0
Tokenizer ClassQwen2Tokenizer
Padding Token<|vision_pad|>
Vocabulary Size152064
Torch Data Typebfloat16
Errorsreplace

Best Alternatives to Qwen2 VL 72B Instruct

Best Alternatives
Context / RAM
Downloads
Likes
Qwen2 VL 72B Instruct32K / 146.8 GB60157311
Qwen2 VL 72B Instruct Bnb 4bit32K / 41.8 GB3955
Qwen2 VL 72B Instruct 8bit32K / 77.8 GB794
Qwen2 VL 72B Instruct 4bit32K / 41.3 GB725
Qwen2 VL 72B Instruct AWQ32K / 43 GB8719050
...wen2 VL 72B Instruct GPTQ Int432K / 43 GB53630
...wen2 VL 72B Instruct GPTQ Int832K / 78.4 GB12611
Note: green Score (e.g. "73.2") means that the model is better than unsloth/Qwen2-VL-72B-Instruct.