QW

Qwen2 VL 72B Instruct

QwenGGUF by bartowskiUpdated 2024-12-18
Download on Hugging Face
Parameters72.7B
Context32K
Layers80
Architectureqwen2vl
Smallest quant25.5 GB
Quick answer

Qwen2 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 24 quants, from 25.5 GB (IQ2_XXS) to 77.3 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 10.7 GB.

Qwen2 VL 72B Instruct – 72.7B parameter vision‑language model

Qwen2 VL 72B Instruct is a 72.7B parameter model that supports image and video understanding. It is instruction‑tuned and can process arbitrary image resolutions. The model is available in multiple GGUF quantizations.

Good at

  • Vision‑language instruction following
  • Multilingual image text comprehension
  • Video content analysis

Limits

  • No vision support in some quants
  • Large VRAM requirement for high‑quality quants
  • License is other

Best for

  • Developing multimodal assistants
  • Analyzing high‑resolution images
  • Processing long video streams

Who it’s for. Developers and researchers needing a large vision‑language model for instruction‑driven tasks. The model is suitable for applications that require detailed visual understanding and multilingual support.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ2_XXS25.5 GB 28.7 GB
Too big Get file →
IQ2_XS27.1 GB 30.2 GB
Too big Get file →
IQ2_S27.9 GB 31.1 GB
Too big Get file →
IQ2_M29.3 GB 32.5 GB
Too big Get file →
Q2_K29.8 GB 33.0 GB
Too big Get file →
Q2_K_L31.0 GB 34.2 GB
Too big Get file →
IQ3_XS32.8 GB 36.0 GB
Too big Get file →
Q3_K_S34.5 GB 37.7 GB
Too big Get file →
IQ3_M35.5 GB 38.7 GB
Too big Get file →
Q3_K_M37.7 GB 40.9 GB
Too big Get file →
Q3_K_L39.5 GB 42.7 GB
Too big Get file →
IQ4_XS39.7 GB 42.9 GB
Too big Get file →
Q3_K_XL40.6 GB 43.8 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_K_M47.4 GB 50.6 GB
Too big Get file →
Q4_K_L48.3 GB 51.5 GB
Too big Get file →
Q5_K_S51.4 GB (2 parts) 54.6 GB
Too big Get file →
Q5_K_M54.4 GB (2 parts) 57.6 GB
Too big Get file →
Q5_K_L55.2 GB (2 parts) 58.4 GB
Too big Get file →
Q6_K64.3 GB (2 parts) 67.5 GB
Too big Get file →
Q6_K_L65.0 GB (2 parts) 68.1 GB
Too big Get file →
Q8_077.3 GB (2 parts) 80.4 GB
Too big Get file →

For 8 GB VRAM, use IQ2_XXS (25.49 GB file, 28.7 GB memory at 8k context). For 12 GB VRAM, IQ2_XS (27.06 GB file, 30.2 GB memory). For 16 GB VRAM, Q2_K (29.81 GB file, 33 GB memory). Larger VRAM allows higher‑quality quants such as Q4_K_M (47.42 GB file, 50.6 GB memory).

What GPU do you need for Qwen2 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_S (27.9 GB file, about 31.1 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 VL 72B Instruct quant should you choose?

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

The Q8_0 file is 77.3 GB, about 1.6 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is IQ2_XXS at 25.5 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 context32,768 tokens
KV cache (fp16)320 KB per token

Source

Quantized bybartowski
FamilyQwen
Licenseother
Downloads (HF)1,579
Last updated2024-12-18

Frequently asked questions about Qwen2 VL 72B Instruct

How much VRAM does Qwen2 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 VL 72B Instruct on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 28.7 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Qwen2 VL 72B Instruct GGUF?

It depends on the quant: IQ2_XXS is 25.5 GB, IQ2_XS is 27.1 GB, IQ2_S is 27.9 GB, IQ2_M is 29.3 GB, Q2_K is 29.8 GB, Q2_K_L is 31.0 GB and 18 more.

What context length does Qwen2 VL 72B Instruct support?

The GGUF header lists a trained context length of 32,768 tokens (32K). 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 VL 72B Instruct GGUF?

The files are on Hugging Face in the bartowski/Qwen2-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 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 VL 72B Instruct on 8 GB VRAM?

Use the IQ2_XXS quant, which requires about 28.7 GB memory at 8k context. It will not fit in 8 GB VRAM, so a smaller quant or lower context length is needed.

Does the model support video input?

Yes, the model can understand videos longer than 20 minutes for question answering and content creation.

Is the model multilingual?

The model supports English, Chinese, and many European languages, Japanese, Korean, Arabic, Vietnamese, and more within images.

Other GGUFs of Qwen2-VL-72B-Instruct

Similar models

Browse all →

More from bartowski

All by bartowski →

More Qwen models

All Qwen →

Other large models

All large models →