QW

Qwen2.5 72B Instruct

QwenGGUF by lmstudio-communityUpdated 2024-09-19
Download on Hugging Face
Parameters72.7B
Context32K
Layers80
Architectureqwen2
Smallest quant39.5 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 4 quants, from 39.5 GB (Q3_K_L) 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 – large instruction‑tuned language model

Qwen2.5 72B Instruct is a 72.7B parameter causal language model with 80 layers and 64 Q heads. It supports up to 128K context tokens and 8K token generation. The model is multilingual and excels in coding, mathematics, and structured data tasks.

Good at

  • Long‑context generation
  • Multilingual support
  • Structured data handling

Limits

  • Large VRAM requirement
  • No vision support
  • License is other

Best for

  • Chatbots needing long context
  • Code generation in multiple languages
  • Generating structured JSON output

Who it’s for. Developers and researchers who need a high‑capacity instruction‑tuned model for long‑form text and structured data tasks. The model is suitable for environments with sufficient GPU memory and a need for multilingual capabilities.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q3_K_L39.5 GB 42.7 GB
Too big Get file →
Q4_K_M47.4 GB 50.6 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 →

For 8 GB VRAM, use Q3_K_L (39.51 GB file, ~42.7 GB memory at 8K context). For 12 GB VRAM, Q4_K_M (47.42 GB file, ~50.6 GB memory). For 16 GB VRAM, Q6_K split into 2 shards (64.35 GB file, ~67.5 GB memory).

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: no quant fits at an 8K context.
  • 48 GB VRAM: the best quant that fits is Q3_K_L (39.5 GB file, about 42.7 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 Q3_K_L at 39.5 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

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 bylmstudio-community
FamilyQwen
Licenseother
Downloads (HF)1,270
Last updated2024-09-19

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 42.7 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: Q3_K_L is 39.5 GB, Q4_K_M is 47.4 GB, Q6_K is 64.3 GB, Q8_0 is 77.3 GB.

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 lmstudio-community/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.

Can I run Qwen2.5 72B Instruct on 8 GB VRAM?

Only with the Q3_K_L quantization, which requires about 42.7 GB of VRAM at 8K context, so 8 GB VRAM is insufficient.

Does the model support image input?

No, the model has no vision capability.

What is the maximum context length?

The model supports up to 128K tokens with yarn rope settings and generates up to 8K tokens.

Other GGUFs of Qwen2.5-72B-Instruct

Similar models

Browse all →

More from lmstudio-community

All by lmstudio-community →

More Qwen models

All Qwen →

Other large models

All large models →