QU

Quyen 22B Merge

QuyenGGUF by DisOOMUpdated 2024-03-30
Download on Hugging Face
Parameters22B
Context32K
Layers65
Architectureqwen2
Smallest quant15.3 GB
Quick answer

Quyen 22B Merge needs about 30.6 GB of memory at Q6_K (a 19.2 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 3 quants, from 15.3 GB (Q5_0) to 23.4 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 43.6 GB.

Quyen 22B Merge is a 22B-parameter Quyen model in GGUF format, quantized by DisOOM. Its trained context length is 32K tokens. The repository has 3 quant files, from 15.3 GB (Q5_0) to 23.4 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q5_015.3 GB 26.7 GB
Too big Get file →
Q6_K19.2 GB 30.6 GB
Too big Get file →
Q8_023.4 GB 34.8 GB
Too big Get file →

What GPU do you need for Quyen 22B Merge?

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 Q6_K (19.2 GB file, about 30.6 GB in use).
  • 48 GB VRAM: the best quant that fits is Q8_0 (23.4 GB file, about 34.8 GB in use).

Which Quyen 22B Merge quant should you choose?

Q6_K (19.2 GB) is the middle option in this repository. Very close to the original quality for most uses, at a clearly larger size than 4-bit.

If memory is tight, the smallest file is Q5_0 at 15.3 GB, with the quality trade-offs that come with fewer bits. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen2
Parameters22B
Layers65
Trained context32,768 tokens
KV cache (fp16)1300 KB per token

Source

Quantized byDisOOM
FamilyQuyen
Licenseother
Downloads (HF)94
Last updated2024-03-30

Frequently asked questions about Quyen 22B Merge

How much VRAM does Quyen 22B Merge need?

About 30.6 GB at Q6_K with an 8K context window. That is the 19.2 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 Quyen 22B Merge on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 26.7 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Quyen 22B Merge GGUF?

It depends on the quant: Q5_0 is 15.3 GB, Q6_K is 19.2 GB, Q8_0 is 23.4 GB.

What context length does Quyen 22B Merge support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 10.9 GB at 8K and 43.6 GB at 32K.

Where can I download Quyen 22B Merge GGUF?

The files are on Hugging Face in the DisOOM/Quyen-22B-Merge-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 Quyen 22B Merge 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.

Similar models

Browse all →

More from DisOOM

All by DisOOM →

More Quyen models

All Quyen →

Other medium models

All medium models →