YI

Edgerunners_yi-9b-may-ortho-baukit-30fail-3000total-bf16

YiGGUF by lucyknadaUpdated 2024-05-13
Download on Hugging Face
Parameters8.83B
Context4K
Layers48
Architecturellama
Smallest quant4.3 GB
Quick answer

Edgerunners_yi-9b-may-ortho-baukit-30fail-3000total-bf16 needs about 6.6 GB of memory at BF16 (a 5.3 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 4 quants, from 4.3 GB (BF16) to 7.2 GB (BF16).

Edgerunners_yi-9b-may-ortho-baukit-30fail-3000total-bf16 is a 8.83B-parameter Yi model in GGUF format, quantized by lucyknada. Its trained context length is 4K tokens. The repository has 4 quant files, from 4.3 GB (BF16) to 7.2 GB (BF16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
BF164.3 GB 5.2 GB
Fits Get file →
BF165.3 GB 6.2 GB
Fits Get file →
BF166.3 GB 7.2 GB
Fits Get file →
BF167.2 GB 8.1 GB
Too big Get file →

What GPU do you need for Edgerunners_yi-9b-may-ortho-baukit-30fail-3000total-bf16?

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: the best quant that fits is BF16 (4.3 GB file, about 5.6 GB in use).
  • 8 GB VRAM: the best quant that fits is BF16 (6.3 GB file, about 7.6 GB in use).
  • 12 GB VRAM: the best quant that fits is BF16 (7.2 GB file, about 8.6 GB in use).

Which Edgerunners_yi-9b-may-ortho-baukit-30fail-3000total-bf16 quant should you choose?

BF16 (5.3 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.

If memory is tight, the smallest file is BF16 at 4.3 GB, with the quality trade-offs that come with fewer bits. 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

Architecturellama
Parameters8.83B
Layers48
Trained context4,096 tokens
KV cache (fp16)96 KB per token

Source

Quantized bylucyknada
FamilyYi
Downloads (HF)20
Last updated2024-05-13

Frequently asked questions about Edgerunners_yi-9b-may-ortho-baukit-30fail-3000total-bf16

How much VRAM does Edgerunners_yi-9b-may-ortho-baukit-30fail-3000total-bf16 need?

About 6.6 GB at BF16 with an 8K context window. That is the 5.3 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 Edgerunners_yi-9b-may-ortho-baukit-30fail-3000total-bf16 on an 8 GB GPU?

Yes, with BF16: the 6.3 GB file needs about 7.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Edgerunners_yi-9b-may-ortho-baukit-30fail-3000total-bf16 GGUF?

It depends on the quant: BF16 is 4.3 GB, BF16 is 5.3 GB, BF16 is 6.3 GB, BF16 is 7.2 GB.

What context length does Edgerunners_yi-9b-may-ortho-baukit-30fail-3000total-bf16 support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 0.8 GB at 8K and 0.4 GB at 4K.

Where can I download Edgerunners_yi-9b-may-ortho-baukit-30fail-3000total-bf16 GGUF?

The files are on Hugging Face in the lucyknada/Edgerunners_yi-9b-may-ortho-baukit-30fail-3000total-bf16-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 Edgerunners_yi-9b-may-ortho-baukit-30fail-3000total-bf16 use?

Hugging Face lists the license as cc-by-nc-4.0. 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 lucyknada

All by lucyknada →

More Yi models

All Yi →

Other small models

All small models →