AY

aya-23-8B

AyaGGUF by lmstudio-communityUpdated 2024-05-23
Download on Hugging Face
Parameters8.03B
Context8K
Layers32
Architecturecommand-r
Smallest quant4.5 GB
Quick answer

aya-23-8B needs about 6.6 GB of memory at Q4_K_M (a 5.1 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 7 quants, from 4.5 GB (Q3_K_L) to 16.1 GB (F16).

aya-23-8B is a 8.03B-parameter Aya model in GGUF format, quantized by lmstudio-community. Its trained context length is 8K tokens. The repository has 7 quant files, from 4.5 GB (Q3_K_L) to 16.1 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q3_K_L4.5 GB 6.1 GB
Fits Get file →
IQ4_NL4.8 GB 6.4 GB
Fits Get file →
Q4_K_M5.1 GB 6.6 GB
Fits Get file →
Q5_K_M5.8 GB 7.4 GB
Tight Get file →
Q6_K6.6 GB 8.2 GB
Too big Get file →
Q8_08.5 GB 10.1 GB
Too big Get file →
F1616.1 GB 17.6 GB
Too big Get file →

What GPU do you need for aya-23-8B?

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: the best quant that fits is Q5_K_M (5.8 GB file, about 7.4 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (8.5 GB file, about 10.1 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (8.5 GB file, about 10.1 GB in use).
  • 24 GB VRAM: the best quant that fits is F16 (16.1 GB file, about 17.6 GB in use).

Which aya-23-8B quant should you choose?

Q4_K_M is the usual starting point for aya-23-8B: it balances file size and quality well. Here it is a 5.1 GB file.

The Q8_0 file is 8.5 GB, about 1.7 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is Q3_K_L at 4.5 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturecommand-r
Parameters8.03B
Layers32
Trained context8,192 tokens
KV cache (fp16)128 KB per token

Source

Quantized bylmstudio-community
FamilyAya
Downloads (HF)230
Last updated2024-05-23

Frequently asked questions about aya-23-8B

How much VRAM does aya-23-8B need?

About 6.6 GB at Q4_K_M with an 8K context window. That is the 5.1 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 aya-23-8B on an 8 GB GPU?

Yes, with Q5_K_M: the 5.8 GB file needs about 7.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of aya-23-8B GGUF?

It depends on the quant: Q3_K_L is 4.5 GB, IQ4_NL is 4.8 GB, Q4_K_M is 5.1 GB, Q5_K_M is 5.8 GB, Q6_K is 6.6 GB, Q8_0 is 8.5 GB and 1 more.

What context length does aya-23-8B support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 1.1 GB at 8K and 1.1 GB at 8K.

Where can I download aya-23-8B GGUF?

The files are on Hugging Face in the lmstudio-community/aya-23-8B-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 aya-23-8B 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.

Other GGUFs of aya-23-8B

Similar models

Browse all →

More from lmstudio-community

All by lmstudio-community →

More Aya models

All Aya →

Other small models

All small models →