YI

Yi-1.5-9B-32K

YiGGUF by ZeroWwUpdated 2024-06-25
Download on Hugging Face
Parameters8.83B
Context32K
Layers48
Architecturellama
Smallest quant6.9 GB
Quick answer

Yi-1.5-9B-32K needs about 9.2 GB of memory at Q6_K (a 7.9 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 4 quants, from 6.9 GB (Q5_K) to 17.7 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 3.2 GB.

Yi-1.5-9B-32K is a 8.83B-parameter Yi model in GGUF format, quantized by ZeroWw. Its trained context length is 32K tokens. The repository has 4 quant files, from 6.9 GB (Q5_K) to 17.7 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q5_K6.9 GB 8.2 GB
Too big Get file →
Q6_K7.9 GB 9.2 GB
Too big Get file →
Q8_09.9 GB 11.2 GB
Too big Get file →
F1617.7 GB 19.0 GB
Too big Get file →

What GPU do you need for Yi-1.5-9B-32K?

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: the best quant that fits is Q8_0 (9.9 GB file, about 11.2 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (9.9 GB file, about 11.2 GB in use).
  • 24 GB VRAM: the best quant that fits is F16 (17.7 GB file, about 19.0 GB in use).

Which Yi-1.5-9B-32K quant should you choose?

Q6_K (7.9 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_K at 6.9 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

Architecturellama
Parameters8.83B
Layers48
Trained context32,768 tokens
KV cache (fp16)96 KB per token

Source

Quantized byZeroWw
FamilyYi
Licensemit
Downloads (HF)31
Last updated2024-06-25

Frequently asked questions about Yi-1.5-9B-32K

How much VRAM does Yi-1.5-9B-32K need?

About 9.2 GB at Q6_K with an 8K context window. That is the 7.9 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 Yi-1.5-9B-32K on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 8.2 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Yi-1.5-9B-32K GGUF?

It depends on the quant: Q5_K is 6.9 GB, Q6_K is 7.9 GB, Q8_0 is 9.9 GB, F16 is 17.7 GB.

What context length does Yi-1.5-9B-32K support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 0.8 GB at 8K and 3.2 GB at 32K.

Where can I download Yi-1.5-9B-32K GGUF?

The files are on Hugging Face in the ZeroWw/Yi-1.5-9B-32K-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 Yi-1.5-9B-32K use?

Hugging Face lists the license as mit. 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 ZeroWw

All by ZeroWw →

More Yi models

All Yi →

Other small models

All small models →