AY

Ayla Light XL i1

AylaGGUF by mradermacherUpdated 2025-02-18
Download on Hugging Face
Parameters17.7B
Context1000K
Layers60
Architecturellama
Smallest quant4.1 GB
Quick answer

Ayla Light XL i1 needs about 13.3 GB of memory at Q4_K_M (a 10.7 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 24 quants, from 4.1 GB (IQ1_S) to 14.5 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 8.1 GB.

Ayla Light XL i1 is a 17.7B-parameter Ayla model in GGUF format, quantized by mradermacher. Its trained context length is 1000K tokens. The repository has 24 quant files, from 4.1 GB (IQ1_S) to 14.5 GB (Q6_K).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S4.1 GB 6.7 GB
Fits Get file →
IQ1_M4.5 GB 7.0 GB
Fits Get file →
IQ2_XXS5.0 GB 7.6 GB
Tight Get file →
IQ2_XS5.5 GB 8.0 GB
Too big Get file →
IQ2_S5.8 GB 8.3 GB
Too big Get file →
IQ2_M6.3 GB 8.8 GB
Too big Get file →
Q2_K_S6.3 GB 8.9 GB
Too big Get file →
Q2_K6.8 GB 9.3 GB
Too big Get file →
IQ3_XXS7.0 GB 9.6 GB
Too big Get file →
IQ3_XS7.5 GB 10.0 GB
Too big Get file →
Q3_K_S7.9 GB 10.4 GB
Too big Get file →
IQ3_S7.9 GB 10.4 GB
Too big Get file →
IQ3_M8.2 GB 10.7 GB
Too big Get file →
Q3_K_M8.7 GB 11.2 GB
Too big Get file →
Q3_K_L9.4 GB 11.9 GB
Too big Get file →
IQ4_XS9.7 GB 12.2 GB
Too big Get file →
Q4_010.2 GB 12.7 GB
Too big Get file →
IQ4_NL10.2 GB 12.7 GB
Too big Get file →
Q4_K_S10.2 GB 12.7 GB
Too big Get file →
Q4_K_M10.7 GB 13.3 GB
Too big Get file →
Q4_111.2 GB 13.7 GB
Too big Get file →
Q5_K_S12.3 GB 14.8 GB
Too big Get file →
Q5_K_M12.6 GB 15.1 GB
Too big Get file →
Q6_K14.5 GB 17.0 GB
Too big Get file →

What GPU do you need for Ayla Light XL i1?

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 IQ2_XS (5.5 GB file, about 8.0 GB in use).
  • 12 GB VRAM: the best quant that fits is Q3_K_L (9.4 GB file, about 11.9 GB in use).
  • 16 GB VRAM: the best quant that fits is Q5_K_M (12.6 GB file, about 15.1 GB in use).
  • 24 GB VRAM: the best quant that fits is Q6_K (14.5 GB file, about 17.0 GB in use).

Which Ayla Light XL i1 quant should you choose?

Q4_K_M is the usual starting point for Ayla Light XL i1: it balances file size and quality well. Here it is a 10.7 GB file.

If memory is tight, the smallest file is IQ1_S at 4.1 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

Architecturellama
Parameters17.7B
Layers60
Trained context1,024,000 tokens
KV cache (fp16)240 KB per token

Source

Quantized bymradermacher
FamilyAyla
Downloads (HF)102
Last updated2025-02-18

Frequently asked questions about Ayla Light XL i1

How much VRAM does Ayla Light XL i1 need?

About 13.3 GB at Q4_K_M with an 8K context window. That is the 10.7 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 Ayla Light XL i1 on an 8 GB GPU?

Yes, with IQ2_XS: the 5.5 GB file needs about 8.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Ayla Light XL i1 GGUF?

It depends on the quant: IQ1_S is 4.1 GB, IQ1_M is 4.5 GB, IQ2_XXS is 5.0 GB, IQ2_XS is 5.5 GB, IQ2_S is 5.8 GB, IQ2_M is 6.3 GB and 18 more.

What context length does Ayla Light XL i1 support?

The GGUF header lists a trained context length of 1,024,000 tokens (1000K). The KV cache grows with the context you use: about 2.0 GB at 8K and 8.1 GB at 32K.

Where can I download Ayla Light XL i1 GGUF?

The files are on Hugging Face in the mradermacher/Ayla-Light-XL-i1-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Ayla models

All Ayla →

Other medium models

All medium models →