AY

aya-23-8B

AyaGGUF by legraphistaUpdated 2024-05-26
Download on Hugging Face
Parameters8B
Context8K
Layers32
Architecturecommand-r
Smallest quant2.2 GB
Quick answer

aya-23-8B needs about 5.5 GB of memory at IQ3_S (a 3.9 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 24 quants, from 2.2 GB (IQ1_S) to 16.1 GB.

aya‑23‑8B, 8B‑parameter command‑r model, quantized for llama.cpp

aya‑23‑8B is an 8‑billion‑parameter command‑r model from the Aya family. It is available in multiple llama.cpp quantizations, ranging from IQ1_S to Q8_0. The model supports up to 8192 context tokens and is licensed under cc‑by‑nc‑4.0.

Good at

  • Large context handling
  • Versatile quantization options
  • Open‑source licensing

Limits

  • No vision support
  • Requires 8‑k context for estimates
  • License restricts commercial use

Best for

  • Chatbots needing long context
  • Research prototyping with low VRAM
  • Educational demos

Who it’s for. Developers and researchers who need a large‑parameter command‑r model that can be run on consumer hardware. The model is suitable for non‑commercial projects and educational purposes.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S2.2 GB 3.8 GB
Fits Get file →
IQ1_M2.4 GB 3.9 GB
Fits Get file →
IQ2_XXS2.6 GB 4.2 GB
Fits Get file →
IQ2_XS2.8 GB 4.4 GB
Fits Get file →
IQ2_S2.9 GB 4.5 GB
Fits Get file →
IQ2_M3.1 GB 4.7 GB
Fits Get file →
Q2_K_S3.2 GB 4.8 GB
Fits Get file →
IQ3_XXS3.4 GB 5.0 GB
Fits Get file →
Q2_K3.4 GB 5.0 GB
Fits Get file →
IQ3_XS3.7 GB 5.3 GB
Fits Get file →
Q3_K_S3.9 GB 5.4 GB
Fits Get file →
IQ3_S3.9 GB 5.5 GB
Fits Get file →
IQ3_M4.0 GB 5.6 GB
Fits Get file →
Q3_K4.2 GB 5.8 GB
Fits Get file →
Q3_K_L4.5 GB 6.1 GB
Fits Get file →
IQ4_XS4.6 GB 6.2 GB
Fits Get file →
IQ4_NL4.8 GB 6.4 GB
Fits Get file →
Q4_K_S4.8 GB 6.4 GB
Fits Get file →
Q4_K5.1 GB 6.6 GB
Fits Get file →
Q5_K_S5.7 GB 7.2 GB
Tight Get file →
Q5_K5.8 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 →
—16.1 GB 17.6 GB
Too big Get file →

For 8‑GB VRAM, use IQ2_S (file size 2.9 GB, estimated 4.5 GB memory). For 12‑GB VRAM, Q4_K (5.06 GB, 6.6 GB memory). For 16‑GB VRAM, Q5_K (5.8 GB, 7.4 GB memory). Estimates are approximate.

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: the best quant that fits is IQ1_M (2.4 GB file, about 3.9 GB in use).
  • 6 GB VRAM: the best quant that fits is Q3_K (4.2 GB file, about 5.8 GB in use).
  • 8 GB VRAM: the best quant that fits is Q5_K (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 the main file (16.1 GB file, about 17.6 GB in use).

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

IQ3_S (3.9 GB) is the middle option in this repository. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

If memory is tight, the smallest file is IQ1_S at 2.2 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturecommand-r
Parameters8B
Layers32
Trained context8,192 tokens
KV cache (fp16)128 KB per token

Source

Quantized bylegraphista
FamilyAya
Downloads (HF)2,673
Last updated2024-05-26

Frequently asked questions about aya-23-8B

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

About 5.5 GB at IQ3_S with an 8K context window. That is the 3.9 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 aya-23-8B on an 8 GB GPU?

Yes, with Q5_K: 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: IQ1_S is 2.2 GB, IQ1_M is 2.4 GB, IQ2_XXS is 2.6 GB, IQ2_XS is 2.8 GB, IQ2_S is 2.9 GB, IQ2_M is 3.1 GB and 18 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 legraphista/aya-23-8B-IMat-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.

Can I run aya‑23‑8B on 8 GB VRAM?

Yes, the IQ2_S quantization requires about 4.5 GB memory at 8‑k context, fitting within 8 GB VRAM.

Does the model support image input?

No, aya‑23‑8B does not include vision capabilities.

Is the model free for commercial use?

The model is licensed cc‑by‑nc‑4.0, so it is not allowed for commercial use without permission.

Other GGUFs of aya-23-8B

Similar models

Browse all →

More from legraphista

All by legraphista →

More Aya models

All Aya →

Other small models

All small models →