QW

Qwen2.5 72B

QwenGGUF by mradermacherUpdated 2024-10-11
Download on Hugging Face
Parameters72.7B
Context128K
Layers80
Architectureqwen2
Smallest quant22.7 GB
Quick answer

Qwen2.5 72B 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 22.7 GB (IQ1_S) to 47.4 GB (Q4_K_M). Longer context needs more: at 32K tokens the KV cache alone adds about 10.7 GB.

Qwen2.5 72B – 72.7B parameter causal language model

Qwen2.5 72B is a 72.7B parameter causal language model with a context length of 131,072 tokens. It supports long‑context generation up to 8K tokens and multilingual capabilities across 29 languages. The base model is intended for further fine‑tuning rather than direct conversation use.

Good at

  • Long‑context generation
  • Multilingual text handling
  • Structured data output

Limits

  • Large memory requirement for base model
  • No vision support
  • Requires post‑training for conversational use

Best for

  • Research on large‑scale language modeling
  • Fine‑tuning for specialized tasks
  • Generating long structured documents

Who it’s for. Researchers and developers who need a large, multilingual causal language model for further fine‑tuning or specialized applications. The base model is not recommended for direct conversational deployment.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S22.7 GB 25.9 GB
Too big Get file →
IQ1_M23.7 GB 26.9 GB
Too big Get file →
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_K_S29.6 GB 32.8 GB
Too big Get file →
Q2_K29.8 GB 33.0 GB
Too big Get file →
IQ3_XXS31.8 GB 35.0 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_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 →
Q4_041.2 GB 44.4 GB
Too big Get file →
Q4_041.2 GB 44.4 GB
Too big Get file →
Q4_041.2 GB 44.4 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_M47.4 GB 50.6 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (22.69 GB file, 25.9 GB memory at 8K context). For 12 GB VRAM, IQ1_M (23.74 GB file, 26.9 GB memory). For 16 GB VRAM, IQ2_XS (27.06 GB file, 30.2 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 Qwen2.5 72B?

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 Qwen2.5 72B quant should you choose?

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

If memory is tight, the smallest file is IQ1_S at 22.7 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

Architectureqwen2
Parameters72.7B
Layers80
Trained context131,072 tokens
KV cache (fp16)320 KB per token

Source

Quantized bymradermacher
FamilyQwen
Licenseother
Downloads (HF)3,642
Last updated2024-10-11

Frequently asked questions about Qwen2.5 72B

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

Not at an 8K context. The smallest file needs about 25.9 GB, so you would need a larger GPU or CPU offloading.

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

It depends on the quant: IQ1_S is 22.7 GB, IQ1_M is 23.7 GB, IQ2_XXS is 25.5 GB, IQ2_XS is 27.1 GB, IQ2_S is 27.9 GB, IQ2_M is 29.3 GB and 18 more.

What context length does Qwen2.5 72B support?

The GGUF header lists a trained context length of 131,072 tokens (128K). 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 GGUF?

The files are on Hugging Face in the mradermacher/Qwen2.5-72B-i1-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 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 72B on 8 GB VRAM?

No. The smallest quant requires 22.69 GB file size and 25.9 GB memory at 8K context, exceeding 8 GB VRAM.

Does this model support vision tasks?

No, the base Qwen2.5 72B model has no vision support.

Is the model ready for chat applications?

No, the base model is intended for further fine‑tuning; it is not recommended for direct conversation use.

Other GGUFs of Qwen2.5-72B

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Qwen models

All Qwen →

Other large models

All large models →