ZA

ZAYA1 8B

ZayaGGUF by 1bit-MONSTERUpdated 2026-09-27
Download on Hugging Face
Parameters8.84B
Context128K
Layers40
Architecturezaya
Smallest quant5.6 GB
Quick answer

ZAYA1 8B needs about 6.4 GB of memory at Q4_K_M (a 5.6 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 2 quants, from 5.6 GB (Q4_K_M) to 17.7 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 1.3 GB.

ZAYA1 8B is a 8.84B-parameter Zaya model in GGUF format, quantized by 1bit-MONSTER. Its trained context length is 128K tokens. The repository has 2 quant files, from 5.6 GB (Q4_K_M) to 17.7 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M5.6 GB 6.4 GB
Fits Get file →
F1617.7 GB 18.6 GB
Too big Get file →

What GPU do you need for ZAYA1 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 (5.6 GB file, about 6.4 GB in use).
  • 12 GB VRAM: the best quant that fits is Q4_K_M (5.6 GB file, about 6.4 GB in use).
  • 16 GB VRAM: the best quant that fits is Q4_K_M (5.6 GB file, about 6.4 GB in use).
  • 24 GB VRAM: the best quant that fits is F16 (17.7 GB file, about 18.6 GB in use).

Which ZAYA1 8B quant should you choose?

Q4_K_M is the usual starting point for ZAYA1 8B: it balances file size and quality well. Here it is a 5.6 GB file.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturezaya
Parameters8.84B (approximate, mixture of experts)
Layers40
Trained context131,072 tokens
KV cache (fp16)40 KB per token

Source

Quantized by1bit-MONSTER
FamilyZaya
Base modelZyphra/ZAYA1-8B
Licenseapache-2.0
Downloads (HF)316
Last updated2026-09-27

Frequently asked questions about ZAYA1 8B

How much VRAM does ZAYA1 8B need?

About 6.4 GB at Q4_K_M with an 8K context window. That is the 5.6 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 ZAYA1 8B on an 8 GB GPU?

Yes, with Q4_K_M: the 5.6 GB file needs about 6.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of ZAYA1 8B GGUF?

It depends on the quant: Q4_K_M is 5.6 GB, F16 is 17.7 GB.

What context length does ZAYA1 8B support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.3 GB at 8K and 1.3 GB at 32K.

Where can I download ZAYA1 8B GGUF?

The files are on Hugging Face in the 1bit-MONSTER/ZAYA1-8B-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 ZAYA1 8B use?

Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Other GGUFs of ZAYA1-8B

Similar models

Browse all →

More from 1bit-MONSTER

All by 1bit-MONSTER →

More Zaya models

All Zaya →

Other small models

All small models →