QW

Qwen2.5-Vl-72B-Instruct

QwenGGUF by unslothUpdated 2025-05-18
Download on Hugging Face
Parameters72.7B
Context125K
Layers80
Architectureqwen2vl
Smallest quant25.7 GB
Quick answer

Qwen2.5-Vl-72B-Instruct needs about 50.6 GB of memory at Q4_K_M (a 47.4 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 23 quants, from 25.7 GB (IQ2_XXS) to 145.4 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 10.7 GB.

Qwen2.5-VL-72B-Instruct – 72.7B multimodal instruction model

Qwen2.5-VL-72B-Instruct is a 72.7B parameter vision‑language model that supports image, video, and structured output tasks. It is trained on 128000 context tokens and can generate bounding boxes, JSON coordinates, and structured data from visual inputs.

Good at

  • Vision‑language reasoning
  • Structured output generation
  • Long video comprehension

Limits

  • Large VRAM requirement
  • No text‑only usage
  • License is other

Best for

  • Document OCR and form extraction
  • Multimodal agent tasks
  • Video event detection

Who it’s for. Developers building visual agents or applications that need detailed image and video analysis. The model is suitable for tasks requiring structured outputs such as invoices or tables.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ2_XXS25.7 GB 28.9 GB
Too big Get file →
IQ2_M29.6 GB 32.8 GB
Too big Get file →
Q2_K29.8 GB 33.0 GB
Too big Get file →
Q2_K_L30.1 GB 33.3 GB
Too big Get file →
Q2_K_XL30.4 GB 33.6 GB
Too big Get file →
IQ3_XXS31.9 GB 35.0 GB
Too big Get file →
Q3_K_S34.5 GB 37.7 GB
Too big Get file →
Q3_K_M37.7 GB 40.9 GB
Too big Get file →
Q3_K_XL38.4 GB 41.5 GB
Too big Get file →
IQ4_XS39.7 GB 42.9 GB
Too big Get file →
IQ4_NL41.3 GB 44.5 GB
Too big Get file →
Q4_041.4 GB 44.6 GB
Too big Get file →
Q4_K_S43.9 GB 47.1 GB
Too big Get file →
Q4_145.7 GB 48.9 GB
Too big Get file →
Q4_K_XL47.3 GB 50.5 GB
Too big Get file →
Q4_K_M47.4 GB 50.6 GB
Too big Get file →
Q5_K_S51.4 GB (2 parts) 54.6 GB
Too big Get file →
Q5_K_XL54.1 GB (2 parts) 57.2 GB
Too big Get file →
Q5_K_M54.4 GB (2 parts) 57.6 GB
Too big Get file →
Q6_K64.3 GB (2 parts) 67.5 GB
Too big Get file →
Q6_K_XL67.3 GB (2 parts) 70.5 GB
Too big Get file →
Q8_K_XL84.7 GB (2 parts) 87.9 GB
Too big Get file →
BF16145.4 GB (3 parts) 148.6 GB
Too big Get file →

For 8 GB VRAM, use IQ2_XXS (25.7 GB file, 28.9 GB memory at 8k). For 16 GB VRAM, Q4_0 (41.38 GB file, 44.6 GB memory) or Q4_K_S (43.89 GB file, 47.1 GB memory). For 24 GB VRAM, Q5_K_S (51.38 GB file, 54.6 GB memory) or Q5_K_XL (54.06 GB file, 57.2 GB memory).

What GPU do you need for Qwen2.5-Vl-72B-Instruct?

These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.

  • 4 GB VRAM: no quant fits at an 8K context.
  • 6 GB VRAM: no quant fits at an 8K context.
  • 8 GB VRAM: no quant fits at an 8K context.
  • 12 GB VRAM: no quant fits at an 8K context.
  • 16 GB VRAM: no quant fits at an 8K context.
  • 24 GB VRAM: no quant fits at an 8K context.
  • 32 GB VRAM: the best quant that fits is IQ2_XXS (25.7 GB file, about 28.9 GB in use).
  • 48 GB VRAM: the best quant that fits is Q4_K_S (43.9 GB file, about 47.1 GB in use).

Which Qwen2.5-Vl-72B-Instruct quant should you choose?

Q4_K_M is the usual starting point for Qwen2.5-Vl-72B-Instruct: it balances file size and quality well. Here it is a 47.4 GB file.

If memory is tight, the smallest file is IQ2_XXS at 25.7 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen2vl
Parameters72.7B
Layers80
Trained context128,000 tokens
KV cache (fp16)320 KB per token

Source

Quantized byunsloth
FamilyQwen
Licenseother
Downloads (HF)3,775
Last updated2025-05-18

Frequently asked questions about Qwen2.5-Vl-72B-Instruct

How much VRAM does Qwen2.5-Vl-72B-Instruct need?

About 50.6 GB at Q4_K_M with an 8K context window. That is the 47.4 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.

Can I run Qwen2.5-Vl-72B-Instruct on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 28.9 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Qwen2.5-Vl-72B-Instruct GGUF?

It depends on the quant: IQ2_XXS is 25.7 GB, IQ2_M is 29.6 GB, Q2_K is 29.8 GB, Q2_K_L is 30.1 GB, Q2_K_XL is 30.4 GB, IQ3_XXS is 31.9 GB and 17 more.

What context length does Qwen2.5-Vl-72B-Instruct support?

The GGUF header lists a trained context length of 128,000 tokens (125K). The KV cache grows with the context you use: about 2.7 GB at 8K and 10.7 GB at 32K.

Where can I download Qwen2.5-Vl-72B-Instruct GGUF?

The files are on Hugging Face in the unsloth/Qwen2.5-VL-72B-Instruct-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Qwen2.5-Vl-72B-Instruct use?

Hugging Face lists the license as other. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Can I run Qwen2.5-VL-72B-Instruct on 8 GB VRAM?

The smallest quant, IQ2_XXS, requires about 28.9 GB VRAM at 8k context, so 8 GB is insufficient.

Does the model support text‑only prompts?

The model is multimodal; it is optimized for image and video inputs and does not provide dedicated text‑only inference.

What license applies to this model?

The model is released under an "other" license; see the Hugging Face license link for details.

Other GGUFs of Qwen2.5-VL-72B-Instruct

Similar models

Browse all →

More from unsloth

All by unsloth →

More Qwen models

All Qwen →

Other large models

All large models →