UA

UAE-Large-V1

UaeGGUF by gaianetUpdated 2024-04-23
Download on Hugging Face
Parameters334M
Context512
Layers24
Architecturebert
Smallest quant0.2 GB
Quick answer

UAE-Large-V1 needs about 1.5 GB of memory at Q5_K_M (a 0.2 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 2 quants, from 0.2 GB (Q5_K_M) to 0.7 GB (F16).

UAE-Large-V1 is a 334M-parameter Uae model in GGUF format, quantized by gaianet. Its trained context length is 512 tokens. The repository has 2 quant files, from 0.2 GB (Q5_K_M) to 0.7 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q5_K_M0.2 GB 0.8 GB
Fits Get file →
F160.7 GB 1.2 GB
Fits Get file →

What GPU do you need for UAE-Large-V1?

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 F16 (0.7 GB file, about 2.0 GB in use).

Which UAE-Large-V1 quant should you choose?

Q5_K_M (0.2 GB) is the middle option in this repository. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturebert
Parameters334M
Layers24
Trained context512 tokens
KV cache (fp16)96 KB per token

Source

Quantized bygaianet
FamilyUae
Downloads (HF)197
Last updated2024-04-23

Frequently asked questions about UAE-Large-V1

How much VRAM does UAE-Large-V1 need?

About 1.5 GB at Q5_K_M with an 8K context window. That is the 0.2 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 UAE-Large-V1 on an 8 GB GPU?

Yes, with F16: the 0.7 GB file needs about 2.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of UAE-Large-V1 GGUF?

It depends on the quant: Q5_K_M is 0.2 GB, F16 is 0.7 GB.

What context length does UAE-Large-V1 support?

The GGUF header lists a trained context length of 512 tokens (512). The KV cache grows with the context you use: about 0.8 GB at 8K and 0.1 GB at 512.

Where can I download UAE-Large-V1 GGUF?

The files are on Hugging Face in the gaianet/UAE-Large-V1-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 gaianet

All by gaianet →

More Uae models

All Uae →

Other tiny models

All tiny models →