QI

qianwen

QianwenGGUF by protimeUpdated 2023-12-12
Download on Hugging Face
Parameters14.2B
Context8K
Layers40
Architectureqwen
Smallest quant28.3 GB
Quick answer

qianwen needs about 35.6 GB of memory at F16 (a 28.3 GB file) with an 8K context window, so it fits on a 48 GB GPU.

qianwen is a 14.2B-parameter Qianwen model in GGUF format, quantized by protime. Its trained context length is 8K tokens. The repository has 1 quant file, from 28.3 GB (F16) to 28.3 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
F1628.3 GB 35.6 GB
Too big Get file →

What GPU do you need for qianwen?

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 F16 (28.3 GB file, about 35.6 GB in use).

Which qianwen quant should you choose?

F16 (28.3 GB) is the middle option in this repository. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen
Parameters14.2B
Layers40
Trained context8,192 tokens
KV cache (fp16)800 KB per token

Source

Quantized byprotime
FamilyQianwen
Repositoryprotime/qianwen
Licenseapache-2.0
Downloads (HF)5
Last updated2023-12-12

Frequently asked questions about qianwen

How much VRAM does qianwen need?

About 35.6 GB at F16 with an 8K context window. That is the 28.3 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 qianwen on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 35.6 GB, so you would need a larger GPU or CPU offloading.

What is the file size of qianwen GGUF?

It depends on the quant: F16 is 28.3 GB.

What context length does qianwen support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 6.7 GB at 8K and 6.7 GB at 8K.

Where can I download qianwen GGUF?

The files are on Hugging Face in the protime/qianwen repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does qianwen 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 Qianwen models

All Qianwen →

Other medium models

All medium models →