QW

Qwen2 72B Instruct

QwenGGUF by QwenUpdated 2024-06-17
Download on Hugging Face
Parameters72.7B
Context32K
Layers80
Architectureqwen2
Smallest quant23.7 GB
Quick answer

Qwen2 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 10 quants, from 23.7 GB (IQ1_M) to 145.4 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 10.7 GB.

Qwen2 72B Instruct – 72.7B parameter instruction‑tuned language model

Qwen2 72B Instruct is a 72.7 billion‑parameter decoder model tuned for instruction following. It supports a 32 768‑token context window and is available in multiple GGUF quantizations. The model is released under an other license and has no detected vision abilities.

Good at

  • Large‑scale instruction following
  • Long‑context reasoning up to 32 768 tokens
  • Multilingual text generation

Limits

  • Requires large VRAM; 8 k context needs 26.9 GB at IQ1_M
  • No vision support
  • License is other, not open source

Best for

  • Enterprise chatbots needing high‑capacity context
  • Research on long‑form content generation
  • Multilingual coding assistance

Who it’s for. Developers and researchers who need a high‑capacity instruction‑tuned model for long‑context tasks. The model is suitable for environments with sufficient GPU memory and where the license terms are acceptable.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_M23.7 GB 26.9 GB
Too big Get file →
Q2_K29.8 GB 33.0 GB
Too big Get file →
Q3_K_M37.7 GB 40.9 GB
Too big Get file →
Q4_041.4 GB 44.6 GB
Too big Get file →
Q4_K_M47.4 GB 50.6 GB
Too big Get file →
Q5_050.3 GB (2 parts) 53.5 GB
Too big Get file →
Q5_K_M54.4 GB (2 parts) 57.6 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 →
—145.4 GB (4 parts) 148.6 GB
Too big Get file →

For 8 GB VRAM, use Q4_0 (44.6 GB memory at 8 k context) or lower. For 16 GB VRAM, Q4_K_M (50.6 GB) or Q5_0 (53.5 GB) are feasible. For 32 GB VRAM, Q6_K (67.5 GB) or Q8_0 (80.4 GB) provide higher precision. Memory estimates are approximate.

What GPU do you need for Qwen2 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 IQ1_M (23.7 GB file, about 26.9 GB in use).
  • 48 GB VRAM: the best quant that fits is Q4_0 (41.4 GB file, about 44.6 GB in use).

Which Qwen2 72B Instruct quant should you choose?

Q4_K_M is the usual starting point for Qwen2 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 IQ1_M at 23.7 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 context32,768 tokens
KV cache (fp16)320 KB per token

Source

Quantized byQwen
FamilyQwen
Licenseother
Downloads (HF)2,003
Last updated2024-06-17

Frequently asked questions about Qwen2 72B Instruct

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

Not at an 8K context. The smallest file needs about 26.9 GB, so you would need a larger GPU or CPU offloading.

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

It depends on the quant: IQ1_M is 23.7 GB, Q2_K is 29.8 GB, Q3_K_M is 37.7 GB, Q4_0 is 41.4 GB, Q4_K_M is 47.4 GB, Q5_0 is 50.3 GB and 4 more.

What context length does Qwen2 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 72B Instruct GGUF?

The files are on Hugging Face in the Qwen/Qwen2-72B-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 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.

Can I run Qwen2 72B Instruct on 8 GB VRAM?

No. The smallest quant requires 26.9 GB at 8 k context, so 8 GB VRAM is insufficient.

Is there a quantization that fits 16 GB VRAM?

Yes, Q4_K_M or Q5_0 can run with about 50–53 GB memory at 8 k context, which is close to 16 GB VRAM but still high; lower VRAM requires further quantization.

Does this model support vision tasks?

No, the model has no detected vision abilities.

Similar models

Browse all →

More from Qwen

All by Qwen →

More Qwen models

All Qwen →

Other large models

All large models →