QW

Qwen.Qwen2.5 VL 72B Instruct

QwenGGUF by DevQuasarUpdated 2025-05-05
Download on Hugging Face
Parameters705M
Context125K
Layers80
Architectureqwen2vl
Smallest quant1.4 GB
Quick answer

Qwen.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 12 quants, from 1.4 GB (F16) to 145.4 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 10.7 GB.

Qwen.Qwen2.5 VL 72B Instruct – a multimodal instruction model

Qwen.Qwen2.5 VL 72B Instruct is a vision‑language model with 0.705 billion parameters. It supports image‑to‑text and video understanding up to 128 000 context tokens. The model is available in multiple GGUF quantizations.

Good at

  • Image captioning
  • Video event detection
  • Structured data extraction

Limits

  • No vision support in some quantizations
  • Large VRAM needed for higher‑quality quants
  • License terms not specified

Best for

  • Multimodal chatbots
  • Document analysis
  • Video summarization

Who it’s for. Developers building multimodal applications that require instruction following and visual reasoning. The model is suitable for research and production use where image and video inputs are needed.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
F161.4 GB 4.6 GB
Fits Get file →
Q2_K29.8 GB 33.0 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_L39.5 GB 42.7 GB
Too big Get file →
Q4_K_S43.9 GB (4 parts) 47.1 GB
Too big Get file →
Q4_K_M47.4 GB (4 parts) 50.6 GB
Too big Get file →
Q5_K_S51.4 GB (4 parts) 54.6 GB
Too big Get file →
Q5_K_M54.4 GB (4 parts) 57.6 GB
Too big Get file →
Q6_K64.3 GB (5 parts) 67.5 GB
Too big Get file →
Q8_077.3 GB (6 parts) 80.4 GB
Too big Get file →
F16145.4 GB (4 parts) 148.6 GB
Too big Get file →

For 8 GB VRAM, use Q2_K (33 GB memory estimate) or Q3_K_S (37.7 GB). For 16 GB VRAM, Q4_K_M (50.6 GB) or Q5_K_M (57.6 GB) are feasible. Larger models require 32 GB or more VRAM.

What GPU do you need for Qwen.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: the best quant that fits is F16 (1.4 GB file, about 4.6 GB in use).
  • 8 GB VRAM: the best quant that fits is F16 (1.4 GB file, about 4.6 GB in use).
  • 12 GB VRAM: the best quant that fits is F16 (1.4 GB file, about 4.6 GB in use).
  • 16 GB VRAM: the best quant that fits is F16 (1.4 GB file, about 4.6 GB in use).
  • 24 GB VRAM: the best quant that fits is F16 (1.4 GB file, about 4.6 GB in use).
  • 32 GB VRAM: the best quant that fits is F16 (1.4 GB file, about 4.6 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 Qwen.Qwen2.5 VL 72B Instruct quant should you choose?

Q4_K_M is the usual starting point for Qwen.Qwen2.5 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 F16 at 1.4 GB, with the quality trade-offs that come with fewer bits. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen2vl
Parameters705M
Layers80
Trained context128,000 tokens
KV cache (fp16)320 KB per token

Source

Quantized byDevQuasar
FamilyQwen
Downloads (HF)590
Last updated2025-05-05

Frequently asked questions about Qwen.Qwen2.5 VL 72B Instruct

How much VRAM does Qwen.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 Qwen.Qwen2.5 VL 72B Instruct on an 8 GB GPU?

Yes, with F16: the 1.4 GB file needs about 4.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Qwen.Qwen2.5 VL 72B Instruct GGUF?

It depends on the quant: F16 is 1.4 GB, Q2_K is 29.8 GB, Q3_K_S is 34.5 GB, Q3_K_M is 37.7 GB, Q3_K_L is 39.5 GB, Q4_K_S is 43.9 GB and 6 more.

What context length does Qwen.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 Qwen.Qwen2.5 VL 72B Instruct GGUF?

The files are on Hugging Face in the DevQuasar/Qwen.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.

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

The smallest quant, Q2_K, estimates 33 GB memory at 8 k context, so 8 GB VRAM is insufficient.

Which quant gives the best balance between size and performance?

Q4_K_M offers a moderate file size of 47.42 GB and 50.6 GB memory estimate, suitable for many setups.

Does the model support video input?

Yes, it can understand videos over 1 hour and capture events within them.

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

Similar models

Browse all →

More from DevQuasar

All by DevQuasar →

More Qwen models

All Qwen →

Other tiny models

All tiny models →