QW

Qwen 72B Chat

QwenGGUF by mradermacherUpdated 2024-10-11
Download on Hugging Face
Parameters72B
Context32K
Layers80
Architectureqwen
Smallest quant15.5 GB
Quick answer

Qwen 72B Chat needs about 67.1 GB of memory at Q4_K_M (a 45.1 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 19 quants, from 15.5 GB (IQ1_S) to 49.9 GB (Q5_K_S). Longer context needs more: at 32K tokens the KV cache alone adds about 85.9 GB.

Qwen 72B Chat – 72‑billion‑parameter LLM with 32k context

Qwen 72B Chat is a 72‑billion‑parameter transformer model from the Qwen family. It supports a 32k token context window and is available in multiple GGUF quantizations. The model is released under a non‑standard license.

Good at

  • Large‑scale multilingual text generation
  • Long‑context dialogue
  • Code and math reasoning

Limits

  • Requires high VRAM for full precision
  • No vision support
  • License not standard

Best for

  • Enterprise chatbots needing long context
  • Research on large‑scale language models
  • Multilingual content creation

Who it’s for. Developers and researchers who need a large, multilingual LLM with extended context. The model is suitable for applications that can accommodate the memory requirements of a 72‑billion‑parameter model.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S15.5 GB 37.5 GB
Too big Get file →
IQ1_M17.0 GB 39.0 GB
Too big Get file →
IQ2_XXS19.4 GB 41.4 GB
Too big Get file →
IQ2_XS21.5 GB 43.5 GB
Too big Get file →
IQ2_S22.6 GB 44.6 GB
Too big Get file →
IQ2_M24.6 GB 46.5 GB
Too big Get file →
Q2_K26.5 GB 48.5 GB
Too big Get file →
IQ3_XXS28.4 GB 50.4 GB
Too big Get file →
IQ3_XS30.4 GB 52.4 GB
Too big Get file →
IQ3_S31.6 GB 53.5 GB
Too big Get file →
Q3_K_S31.6 GB 53.5 GB
Too big Get file →
IQ3_M34.7 GB 56.7 GB
Too big Get file →
Q3_K_M36.7 GB 58.7 GB
Too big Get file →
IQ4_XS38.8 GB 60.8 GB
Too big Get file →
Q3_K_L39.2 GB 61.2 GB
Too big Get file →
Q4_041.1 GB 63.1 GB
Too big Get file →
Q4_K_S41.3 GB 63.2 GB
Too big Get file →
Q4_K_M45.1 GB 67.1 GB
Too big Get file →
Q5_K_S49.9 GB 71.9 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (15.52 GB file, 37.5 GB memory at 8k context). For 12 GB VRAM, IQ1_M (16.98 GB file, 39 GB memory). For 16 GB VRAM, IQ2_XS (21.54 GB file, 43.5 GB memory).

What GPU do you need for Qwen 72B Chat?

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: the best quant that fits is IQ2_M (24.6 GB file, about 46.5 GB in use).

Which Qwen 72B Chat quant should you choose?

Q4_K_M is the usual starting point for Qwen 72B Chat: it balances file size and quality well. Here it is a 45.1 GB file.

If memory is tight, the smallest file is IQ1_S at 15.5 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

Architectureqwen
Parameters72B
Layers80
Trained context32,768 tokens
KV cache (fp16)2560 KB per token

Source

Quantized bymradermacher
FamilyQwen
Licenseother
Downloads (HF)1,188
Last updated2024-10-11

Frequently asked questions about Qwen 72B Chat

How much VRAM does Qwen 72B Chat need?

About 67.1 GB at Q4_K_M with an 8K context window. That is the 45.1 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 72B Chat on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 37.5 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Qwen 72B Chat GGUF?

It depends on the quant: IQ1_S is 15.5 GB, IQ1_M is 17.0 GB, IQ2_XXS is 19.4 GB, IQ2_XS is 21.5 GB, IQ2_S is 22.6 GB, IQ2_M is 24.6 GB and 13 more.

What context length does Qwen 72B Chat support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 21.5 GB at 8K and 85.9 GB at 32K.

Where can I download Qwen 72B Chat GGUF?

The files are on Hugging Face in the mradermacher/Qwen-72B-Chat-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 Qwen 72B Chat 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 Qwen 72B Chat on 8 GB VRAM?

Only with the smallest quantization IQ1_S, which still requires about 37.5 GB of VRAM at 8k context, so 8 GB is insufficient.

Does this model support image inputs?

No, the model has no vision capabilities.

What license applies to this model?

The model is released under a non‑standard license; check the repository for details.

Other GGUFs of Qwen-72B-Chat

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Qwen models

All Qwen →

Other large models

All large models →