QW

Qwen2.5 72B Instruct

QwenGGUF by RichardErkhovUpdated 2024-09-29
Download on Hugging Face
Parameters72.7B
Context32K
Layers80
Architectureqwen2
Smallest quant26.1 GB
Quick answer

Qwen2.5 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 22 quants, from 26.1 GB (IQ4_XS) to 77.3 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 10.7 GB.

Qwen2.5 72B Instruct is a 72.7B-parameter Qwen model in GGUF format, quantized by RichardErkhov. Its trained context length is 32K tokens. The repository has 22 quant files, from 26.1 GB (IQ4_XS) to 77.3 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ4_XS26.1 GB 29.3 GB
Too big Get file →
Q2_K29.8 GB 33.0 GB
Too big Get file →
IQ3_XS32.8 GB 36.0 GB
Too big Get file →
IQ3_S34.5 GB 37.7 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_K37.7 GB 40.9 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_041.2 GB (2 parts) 44.4 GB
Too big Get file →
IQ4_NL41.8 GB (2 parts) 45.0 GB
Too big Get file →
Q4_K_S43.9 GB (2 parts) 47.1 GB
Too big Get file →
Q4_145.7 GB (2 parts) 48.9 GB
Too big Get file →
Q4_K47.4 GB (2 parts) 50.6 GB
Too big Get file →
Q4_K_M47.4 GB (2 parts) 50.6 GB
Too big Get file →
Q5_050.2 GB (2 parts) 53.3 GB
Too big Get file →
Q5_K_S51.4 GB (2 parts) 54.6 GB
Too big Get file →
Q5_K54.4 GB (2 parts) 57.6 GB
Too big Get file →
Q5_K_M54.4 GB (2 parts) 57.6 GB
Too big Get file →
Q5_154.6 GB (2 parts) 57.8 GB
Too big Get file →
Q6_K64.3 GB (2 parts) 67.5 GB
Too big Get file →
Q8_077.3 GB (2 parts) 80.4 GB
Too big Get file →

What GPU do you need for Qwen2.5 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 IQ4_XS (26.1 GB file, about 29.3 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 72B Instruct quant should you choose?

Q4_K_M is the usual starting point for Qwen2.5 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 IQ4_XS at 26.1 GB, with the quality trade-offs that come with fewer bits. The usual sweet spot between file size and quality, and the quant most people start with.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen2
Parameters72.7B
Layers80
Trained context32,768 tokens
KV cache (fp16)320 KB per token

Source

Quantized byRichardErkhov
FamilyQwen
Licenseother
Downloads (HF)339
Last updated2024-09-29

Frequently asked questions about Qwen2.5 72B Instruct

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

Not at an 8K context. The smallest file needs about 29.3 GB, so you would need a larger GPU or CPU offloading.

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

It depends on the quant: IQ4_XS is 26.1 GB, Q2_K is 29.8 GB, IQ3_XS is 32.8 GB, IQ3_S is 34.5 GB, Q3_K_S is 34.5 GB, IQ3_M is 35.5 GB and 16 more.

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

The files are on Hugging Face in the RichardErkhov/Qwen_-_Qwen2.5-72B-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 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.

Similar models

Browse all →

More from RichardErkhov

All by RichardErkhov →

More Qwen models

All Qwen →

Other large models

All large models →