QW

qwen2.5-72b-instruct

QwenGGUF by QwenUpdated 2024-09-20
Download on Hugging Face
Parameters73B
Context32K
Layers80
Architectureqwen2
Smallest quant27.3 GB
Quick answer

qwen2.5-72b-instruct needs about 47.2 GB of memory at Q4_K_M (a 44.0 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 9 quants, from 27.3 GB (Q2_K) to 145.9 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 10.7 GB.

Qwen2.5‑72B‑Instruct in GGUF format for large‑scale instruction following

Qwen2.5‑72B‑Instruct is a 72.7 B‑parameter causal language model. It supports up to 32 768‑token context and 8 192‑token generation, with long‑context support via YARN. The model is instruction‑tuned and multilingual across 29 languages.

Good at

  • Instruction following
  • Long‑text generation
  • Structured data handling

Limits

  • Requires large VRAM for full precision
  • No vision support
  • License is other

Best for

  • Chatbot development
  • Code generation
  • Data extraction tasks

Who it’s for. Developers needing a high‑capacity instruction model for text‑only workloads. Suitable for research and production environments that can accommodate the memory demands.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K27.3 GB (7 parts) 30.5 GB
Too big Get file →
Q3_K_M35.5 GB (9 parts) 38.7 GB
Too big Get file →
Q4_041.4 GB (11 parts) 44.6 GB
Too big Get file →
Q4_K_M44.0 GB (12 parts) 47.2 GB
Too big Get file →
Q5_050.3 GB (13 parts) 53.5 GB
Too big Get file →
Q5_K_M51.7 GB (14 parts) 54.9 GB
Too big Get file →
Q6_K59.9 GB (16 parts) 63.0 GB
Too big Get file →
Q8_077.5 GB (21 parts) 80.7 GB
Too big Get file →
—145.9 GB (42 parts) 149.1 GB
Too big Get file →

For 8 GB VRAM, use Q2_K (27.33 GB file, ~30.5 GB memory at 8 k context). For 16 GB VRAM, Q3_K_M (35.47 GB file, ~38.7 GB memory). For 32 GB VRAM, Q4_0 (41.37 GB file, ~44.6 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: the best quant that fits is Q2_K (27.3 GB file, about 30.5 GB in use).
  • 48 GB VRAM: the best quant that fits is Q4_K_M (44.0 GB file, about 47.2 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 44.0 GB file.

The Q8_0 file is 77.5 GB, about 1.8 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 Q2_K at 27.3 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
Parameters73B
Layers80
Trained context32,768 tokens
KV cache (fp16)320 KB per token

Source

Quantized byQwen
FamilyQwen
Licenseother
Downloads (HF)7,487
Last updated2024-09-20

Frequently asked questions about qwen2.5-72b-instruct

How much VRAM does qwen2.5-72b-instruct need?

About 47.2 GB at Q4_K_M with an 8K context window. That is the 44.0 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 30.5 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: Q2_K is 27.3 GB, Q3_K_M is 35.5 GB, Q4_0 is 41.4 GB, Q4_K_M is 44.0 GB, Q5_0 is 50.3 GB, Q5_K_M is 51.7 GB and 3 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 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.

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

Only with the Q2_K quantization; it requires about 30.5 GB of VRAM at 8 k context, so 8 GB is insufficient.

Does this model support vision tasks?

No, the GGUF version is text‑only and does not include vision capabilities.

What is the maximum context length I can use?

The GGUF model supports up to 32 768 tokens; longer contexts need YARN or the non‑GGUF version.

Other GGUFs of Qwen2.5-72B-Instruct

Similar models

Browse all →

More from Qwen

All by Qwen →

More Qwen models

All Qwen →

Other large models

All large models →