AY

Aya Expanse 8b

AyaGGUF by lmstudio-communityUpdated 2024-10-24
Download on Hugging Face
Parameters8.03B
Context8K
Layers32
Architecturecommand-r
Smallest quant4.5 GB
Quick answer

Aya Expanse 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 4 quants, from 4.5 GB (Q3_K_L) to 8.5 GB (Q8_0).

Aya Expanse 8b – 8.03B parameter command-r model

Aya Expanse 8b is a 8.03B parameter command-r model with a 8192 token context. It is released under CC-BY-NC-4.0 and supports 23 languages. The model is available in four GGUF quantizations.

Good at

  • Multilingual text generation
  • Contextual understanding up to 8192 tokens
  • Open-source community support

Limits

  • CC-BY-NC license requires non-commercial use
  • No vision or audio capabilities
  • Requires C4AI Acceptable Use Policy compliance

Best for

  • Chatbots needing multilingual support
  • Content creation in multiple languages
  • Research prototyping with open-source models

Who it’s for. Developers and researchers building multilingual applications who need a large language model that is open-source and community maintained. The model is suitable for non-commercial projects due to its CC-BY-NC license.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q3_K_L4.5 GB 6.1 GB
Fits Get file →
Q4_K_M5.1 GB 6.6 GB
Fits Get file →
Q6_K6.6 GB 8.2 GB
Too big Get file →
Q8_08.5 GB 10.1 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_M (5.06 GB file, ~6.6 GB memory). For 12 GB VRAM, Q6_K (6.6 GB file, ~8.2 GB memory) is suitable. For 16 GB VRAM or more, Q8_0 (8.54 GB file, ~10.1 GB memory) provides the highest precision.

What GPU do you need for Aya Expanse 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 Q4_K_M (5.1 GB file, about 6.6 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (8.5 GB file, about 10.1 GB in use).

Which Aya Expanse 8b quant should you choose?

Q4_K_M is the usual starting point for Aya Expanse 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)546
Last updated2024-10-24

Frequently asked questions about Aya Expanse 8b

How much VRAM does Aya Expanse 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 Expanse 8b on an 8 GB GPU?

Yes, with Q4_K_M: the 5.1 GB file needs about 6.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Aya Expanse 8b GGUF?

It depends on the quant: Q3_K_L is 4.5 GB, Q4_K_M is 5.1 GB, Q6_K is 6.6 GB, Q8_0 is 8.5 GB.

What context length does Aya Expanse 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 Expanse 8b GGUF?

The files are on Hugging Face in the lmstudio-community/aya-expanse-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 Expanse 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 Expanse 8b on 8 GB VRAM?

Yes, the Q4_K_M quantization requires about 6.6 GB of VRAM at 8192 context, which fits within 8 GB.

Is Aya Expanse 8b suitable for commercial use?

No, the CC-BY-NC-4.0 license restricts commercial use; only non-commercial projects are allowed.

Does the model support vision or audio?

No, Aya Expanse 8b is a text-only model with no vision or audio capabilities.

Other GGUFs of aya-expanse-8b

Similar models

Browse all →

More from lmstudio-community

All by lmstudio-community →

More Aya models

All Aya →

Other small models

All small models →