TI

Tiny Aya Water

TinyGGUF by CohereLabsUpdated 2026-02-17
Download on Hugging Face
Parameters3.35B
Context488K
Layers36
Architecturecohere2
Smallest quant2.0 GB
Quick answer

Tiny Aya Water needs about 3.2 GB of memory at Q4_K_M (a 2.1 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 5 quants, from 2.0 GB (Q4_0) to 6.7 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 2.4 GB.

Tiny Aya Water – a 3.35B parameter cohere2 model

Tiny Aya Water is a 3.35B parameter model based on the cohere2 architecture. It supports a 500000 token training context and is available under a cc‑by‑nc‑4.0 license. The model is multilingual with support for many languages.

Good at

  • Multilingual text generation
  • Lightweight inference
  • Non‑commercial use

Limits

  • No vision support
  • Requires at least 3.1 GB VRAM for Q4_0
  • License restricts commercial use

Best for

  • Chatbots on low‑budget GPUs
  • Research prototyping
  • Educational demos

Who it’s for. Developers and researchers who need a small, multilingual language model for non‑commercial projects. The model is suitable for low‑resource environments and educational settings.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_02.0 GB 3.1 GB
Fits Get file →
Q4_K_M2.1 GB 3.2 GB
Fits Get file →
Q8_03.6 GB 4.7 GB
Fits Get file →
BF166.7 GB 7.8 GB
Tight Get file →
F166.7 GB 7.8 GB
Tight Get file →

For 8 GB VRAM, use Q4_0 (2.03 GB file, 3.1 GB VRAM) or Q4_K_M (2.14 GB file, 3.2 GB VRAM). If more memory is available, Q8_0 (3.57 GB file, 4.7 GB VRAM) offers higher precision. BF16 and F16 require 6.71 GB files and 7.8 GB VRAM.

What GPU do you need for Tiny Aya Water?

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 Q4_K_M (2.1 GB file, about 3.2 GB in use).
  • 6 GB VRAM: the best quant that fits is Q8_0 (3.6 GB file, about 4.7 GB in use).
  • 8 GB VRAM: the best quant that fits is BF16 (6.7 GB file, about 7.8 GB in use).

Which Tiny Aya Water quant should you choose?

Q4_K_M is the usual starting point for Tiny Aya Water: it balances file size and quality well. Here it is a 2.1 GB file.

The Q8_0 file is 3.6 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 Q4_0 at 2.0 GB, with the quality trade-offs that come with fewer bits. The usual sweet spot between file size and quality, and the quant most people start with.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturecohere2
Parameters3.35B
Layers36
Trained context500,000 tokens
KV cache (fp16)72 KB per token

Source

Quantized byCohereLabs
FamilyTiny
Downloads (HF)597
Last updated2026-02-17

Frequently asked questions about Tiny Aya Water

How much VRAM does Tiny Aya Water need?

About 3.2 GB at Q4_K_M with an 8K context window. That is the 2.1 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 Tiny Aya Water on an 8 GB GPU?

Yes, with BF16: the 6.7 GB file needs about 7.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Tiny Aya Water GGUF?

It depends on the quant: Q4_0 is 2.0 GB, Q4_K_M is 2.1 GB, Q8_0 is 3.6 GB, BF16 is 6.7 GB, F16 is 6.7 GB.

What context length does Tiny Aya Water 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 Water GGUF?

The files are on Hugging Face in the CohereLabs/tiny-aya-water-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 Water 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 Tiny Aya Water on 8 GB VRAM?

Yes, the Q4_0 and Q4_K_M quantizations fit within 8 GB VRAM, using approximately 3.1–3.2 GB.

Is Tiny Aya Water suitable for commercial projects?

No. The cc‑by‑nc‑4.0 license allows only non‑commercial use.

What languages does Tiny Aya Water support?

It supports many languages, including English, Dutch, French, Spanish, German, Chinese, Japanese, Korean, and many others listed in its repo card.

Other GGUFs of tiny-aya-water

Similar models

Browse all →

More from CohereLabs

All by CohereLabs →

More Tiny models

All Tiny →

Other tiny models

All tiny models →