QW

qwen quantized

QwenGGUF by fxinwei123Updated 2025-01-05
Download on Hugging Face
Parameters70.6B
Context32K
Layers64
Architectureqwen2
Smallest quant19.9 GB
Quick answer

qwen quantized needs about 50.1 GB of memory at its main file (a 47.4 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 5 quants, from 19.9 GB to 47.4 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 8.6 GB.

qwen quantized is a 70.6B-parameter Qwen model in GGUF format, quantized by fxinwei123. Its trained context length is 32K tokens. The repository has 5 quant files, from 19.9 GB to 47.4 GB.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—19.9 GB 22.5 GB
Too big Get file →
—42.5 GB 45.2 GB
Too big Get file →
—47.4 GB 50.1 GB
Too big Get file →
—47.4 GB 50.1 GB
Too big Get file →
—47.4 GB 50.1 GB
Too big Get file →

What GPU do you need for qwen quantized?

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: the best quant that fits is the main file (19.9 GB file, about 22.5 GB in use).
  • 32 GB VRAM: the best quant that fits is the main file (19.9 GB file, about 22.5 GB in use).
  • 48 GB VRAM: the best quant that fits is the main file (42.5 GB file, about 45.2 GB in use).

Which qwen quantized quant should you choose?

If memory is tight, the smallest file is the first one in the table at 19.9 GB, with the quality trade-offs that come with fewer bits.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen2
Parameters70.6B
Layers64
Trained context32,768 tokens
KV cache (fp16)256 KB per token

Source

Quantized byfxinwei123
FamilyQwen
Licenseapache-2.0
Downloads (HF)42
Last updated2025-01-05

Frequently asked questions about qwen quantized

How much VRAM does qwen quantized need?

About 50.1 GB at its main file 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 qwen quantized on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 22.5 GB, so you would need a larger GPU or CPU offloading.

What is the file size of qwen quantized GGUF?

It depends on the quant: file is 19.9 GB, file is 42.5 GB, file is 47.4 GB, file is 47.4 GB, file is 47.4 GB.

What context length does qwen quantized support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 2.1 GB at 8K and 8.6 GB at 32K.

Where can I download qwen quantized GGUF?

The files are on Hugging Face in the fxinwei123/qwen-quantized 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 quantized use?

Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Similar models

Browse all →

More from fxinwei123

All by fxinwei123 →

More Qwen models

All Qwen →

Other large models

All large models →