QW

Qwen2.5 VL 72B Instruct abliterated deep

QwenGGUF by rvnctoUpdated 2026-02-20
Download on Hugging Face
Parameters72.7B
Context125K
Layers80
Architectureqwen2vl
Smallest quant54.4 GB
Quick answer

Qwen2.5 VL 72B Instruct abliterated deep needs about 57.6 GB of memory at Q5_K_M (a 54.4 GB file) with an 8K context window, which is more than a 48 GB GPU holds. Longer context needs more: at 32K tokens the KV cache alone adds about 10.7 GB.

Qwen2.5 VL 72B Instruct abliterated deep is a 72.7B-parameter Qwen model in GGUF format, quantized by rvncto. Its trained context length is 125K tokens. The repository has 1 quant file, from 54.4 GB (Q5_K_M) to 54.4 GB (Q5_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q5_K_M54.4 GB 57.6 GB
Too big Get file →

What GPU do you need for Qwen2.5 VL 72B Instruct abliterated deep?

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: no quant fits at an 8K context.
  • 48 GB VRAM: no quant fits at an 8K context.

Which Qwen2.5 VL 72B Instruct abliterated deep quant should you choose?

Q5_K_M (54.4 GB) is the middle option in this repository. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.

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 byrvncto
FamilyQwen
Downloads (HF)108
Last updated2026-02-20

Frequently asked questions about Qwen2.5 VL 72B Instruct abliterated deep

How much VRAM does Qwen2.5 VL 72B Instruct abliterated deep need?

About 57.6 GB at Q5_K_M with an 8K context window. That is the 54.4 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 abliterated deep on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 57.6 GB, so you would need a larger GPU or CPU offloading.

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

It depends on the quant: Q5_K_M is 54.4 GB.

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

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

Similar models

Browse all →

More from rvncto

All by rvncto →

More Qwen models

All Qwen →

Other large models

All large models →