Tiny Aya Earth needs about 3.5 GB of memory at Q4_K_M (a 2.4 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 5 quants, from 1.6 GB (IQ3_XXS) to 2.9 GB (Q6_K_L). Longer context needs more: at 32K tokens the KV cache alone adds about 2.4 GB.
Tiny Aya Earth is a 3.35B-parameter Tiny model in GGUF format, quantized by mazrba. Its trained context length is 488K tokens. The repository has 5 quant files, from 1.6 GB (IQ3_XXS) to 2.9 GB (Q6_K_L).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ3_XXS | 1.6 GB | 2.7 GB | Fits | Get file → | |
| IQ4_XS | 2.0 GB | 3.1 GB | Fits | Get file → | |
| Q4_K_M | 2.4 GB | 3.5 GB | Fits | Get file → | |
| Q5_K_M | 2.6 GB | 3.7 GB | Fits | Get file → | |
| Q6_K_L | 2.9 GB | 4.0 GB | Fits | Get file → |
What GPU do you need for Tiny Aya Earth?
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 Q6_K_L (2.9 GB file, about 4.0 GB in use).
Which Tiny Aya Earth quant should you choose?
Q4_K_M is the usual starting point for Tiny Aya Earth: it balances file size and quality well. Here it is a 2.4 GB file.
If memory is tight, the smallest file is IQ3_XXS at 1.6 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
Source
Frequently asked questions about Tiny Aya Earth
How much VRAM does Tiny Aya Earth need?
About 3.5 GB at Q4_K_M with an 8K context window. That is the 2.4 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 Tiny Aya Earth on an 8 GB GPU?
Yes, with Q6_K_L: the 2.9 GB file needs about 4.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Tiny Aya Earth GGUF?
It depends on the quant: IQ3_XXS is 1.6 GB, IQ4_XS is 2.0 GB, Q4_K_M is 2.4 GB, Q5_K_M is 2.6 GB, Q6_K_L is 2.9 GB.
What context length does Tiny Aya Earth support?
The GGUF header lists a trained context length of 500,000 tokens (488K). The KV cache grows with the context you use: about 0.6 GB at 8K and 2.4 GB at 32K.
Where can I download Tiny Aya Earth GGUF?
The files are on Hugging Face in the mazrba/tiny-aya-earth-imatrix-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 Tiny Aya Earth 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.