QW

qwen 14b chat

QwenGGUF by ikawrakowUpdated 2024-01-12
Download on Hugging Face
Parameters14.2B
Context8K
Layers40
Architectureqwen
Smallest quant4.9 GB
Quick answer

qwen 14b chat needs about 14.6 GB of memory at its main file (a 7.4 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 6 quants, from 4.9 GB to 10.0 GB.

qwen 14b chat is a 14.2B-parameter Qwen model in GGUF format, quantized by ikawrakow. Its trained context length is 8K tokens. The repository has 6 quant files, from 4.9 GB to 10.0 GB.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—4.9 GB 12.1 GB
Too big Get file →
—5.2 GB 12.4 GB
Too big Get file →
—7.4 GB 14.6 GB
Too big Get file →
—7.7 GB 14.9 GB
Too big Get file →
—8.6 GB 15.8 GB
Too big Get file →
—10.0 GB 17.2 GB
Too big Get file →

What GPU do you need for qwen 14b chat?

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: the best quant that fits is the main file (8.6 GB file, about 15.8 GB in use).
  • 24 GB VRAM: the best quant that fits is the main file (10.0 GB file, about 17.2 GB in use).

Which qwen 14b chat quant should you choose?

If memory is tight, the smallest file is the first one in the table at 4.9 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

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

Source

Quantized byikawrakow
FamilyQwen
Licenseapache-2.0
Downloads (HF)230
Last updated2024-01-12

Frequently asked questions about qwen 14b chat

How much VRAM does qwen 14b chat need?

About 14.6 GB at its main file with an 8K context window. That is the 7.4 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 14b chat on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 12.1 GB, so you would need a larger GPU or CPU offloading.

What is the file size of qwen 14b chat GGUF?

It depends on the quant: file is 4.9 GB, file is 5.2 GB, file is 7.4 GB, file is 7.7 GB, file is 8.6 GB, file is 10.0 GB.

What context length does qwen 14b chat 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 qwen 14b chat GGUF?

The files are on Hugging Face in the ikawrakow/qwen-14b-chat-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 qwen 14b chat 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 ikawrakow

All by ikawrakow →

More Qwen models

All Qwen →

Other medium models

All medium models →