LLM EXPLORER 57,252 MODELS INDEXED

Qwen2.5 VL 72B Instruct AWQ by Qwen

By Qwen · 282497 downloads
HF Repo ↗ Copy URL

Qwen2.5 VL 72B Instruct AWQ is an open-source language model by Qwen. Features: 72b LLM, VRAM: 43GB, Context: 125K, License: other, Quantized, Instruction-Based, LLM Explorer Score: 0.25.

  Arxiv:2308.12966   Arxiv:2309.00071   Arxiv:2409.12191   4-bit   Awq Base model:quantized:qwen/qwen... Base model:qwen/qwen2.5-vl-72b...   Conversational   En   Endpoints compatible   Image-text-to-text   Instruct   Multimodal   Quantized   Qwen2 5 vl   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/Qwen/Qwen2.5-VL-72B-Instruct-AWQ 

Qwen2.5 VL 72B Instruct AWQ Parameters and Internals

LLM NameQwen2.5 VL 72B Instruct AWQ
Repository 🤗https://huggingface.co/Qwen/Qwen2.5-VL-72B-Instruct-AWQ 
Base Model(s)  Qwen/Qwen2.5-VL-72B-Instruct   Qwen/Qwen2.5-VL-72B-Instruct
Model Size72b
Required VRAM43 GB
Updated2026-08-09
MaintainerQwen
Model Typeqwen2_5_vl
Instruction-BasedYes
Model Files  4.0 GB: 1-of-11   3.9 GB: 2-of-11   4.0 GB: 3-of-11   4.0 GB: 4-of-11   3.9 GB: 5-of-11   4.0 GB: 6-of-11   4.0 GB: 7-of-11   3.9 GB: 8-of-11   4.0 GB: 9-of-11   4.0 GB: 10-of-11   3.3 GB: 11-of-11
Supported Languagesen
AWQ QuantizationYes
Quantization Typeawq
Model ArchitectureQwen2_5_VLForConditionalGeneration
Licenseother
Context Length128000
Model Max Length128000
Transformers Version4.49.0.dev0
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size152064
Torch Data Typebfloat16
Errorsreplace

Best Alternatives to Qwen2.5 VL 72B Instruct AWQ

Best Alternatives
Context / RAM
Downloads
Likes
Qwen2.5 VL 72B Instruct 4bit125K / 42.2 GB13049
Qwen2.5 VL 72B Instruct 3bit125K / 33.3 GB2965
Qwen2.5 VL 72B Instruct 8bit125K / 77.8 GB2142
Qwen2.5 VL 72B Instruct 6bit125K / 59.7 GB1321
Qwen2.5 VL 72B Instruct125K / 146.8 GB546414645
Note: green Score (e.g. "73.2") means that the model is better than Qwen/Qwen2.5-VL-72B-Instruct-AWQ.