ZAYA1 74B Preview needs about 46.7 GB of memory at Q4_K_M (a 45.7 GB file) with an 8K context window, so it fits on a 48 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 2.0 GB.
ZAYA1 74B Preview is a 74.8B-parameter Zaya model in GGUF format, quantized by 1bit-MONSTER. Its trained context length is 256K tokens. The repository has 1 quant file, from 45.7 GB (Q4_K_M) to 45.7 GB (Q4_K_M).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 45.7 GB | 46.7 GB | Too big | Get file → |
What GPU do you need for ZAYA1 74B Preview?
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: no quant fits at an 8K context.
- 12 GB VRAM: no quant fits at an 8K context.
- 16 GB VRAM: no quant fits at an 8K context.
- 24 GB VRAM: no quant fits at an 8K context.
- 32 GB VRAM: no quant fits at an 8K context.
- 48 GB VRAM: the best quant that fits is Q4_K_M (45.7 GB file, about 46.7 GB in use).
Which ZAYA1 74B Preview quant should you choose?
Q4_K_M is the usual starting point for ZAYA1 74B Preview: it balances file size and quality well. Here it is a 45.7 GB file.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about ZAYA1 74B Preview
How much VRAM does ZAYA1 74B Preview need?
About 46.7 GB at Q4_K_M with an 8K context window. That is the 45.7 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 ZAYA1 74B Preview on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 46.7 GB, so you would need a larger GPU or CPU offloading.
What is the file size of ZAYA1 74B Preview GGUF?
It depends on the quant: Q4_K_M is 45.7 GB.
What context length does ZAYA1 74B Preview support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.5 GB at 8K and 2.0 GB at 32K.
Where can I download ZAYA1 74B Preview GGUF?
The files are on Hugging Face in the 1bit-MONSTER/ZAYA1-74B-preview-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 74B Preview 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.