SM

T5 Small

SmallGGUF by cahajUpdated 2024-08-30
Download on Hugging Face
Parameters77M
Context512
Layers6
Architecturet5
Smallest quant0.2 GB
Quick answer

T5 Small needs about 0.8 GB of memory at F16 (a 0.2 GB file) with an 8K context window, so it fits on a 4 GB GPU.

T5 Small is a 77M-parameter Small model in GGUF format, quantized by cahaj. Its trained context length is 512 tokens. The repository has 1 quant file, from 0.2 GB (F16) to 0.2 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
F160.2 GB 0.7 GB
Fits Get file →

What GPU do you need for T5 Small?

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 (0.2 GB file, about 0.8 GB in use).

Which T5 Small quant should you choose?

F16 (0.2 GB) is the middle option in this repository. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturet5
Parameters77M
Layers6
Trained context512 tokens
KV cache (fp16)12 KB per token

Source

Quantized bycahaj
FamilySmall
Licenseapache-2.0
Downloads (HF)33
Last updated2024-08-30

Frequently asked questions about T5 Small

How much VRAM does T5 Small need?

About 0.8 GB at F16 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 T5 Small on an 8 GB GPU?

Yes, with F16: the 0.2 GB file needs about 0.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of T5 Small GGUF?

It depends on the quant: F16 is 0.2 GB.

What context length does T5 Small support?

The GGUF header lists a trained context length of 512 tokens (512). The KV cache grows with the context you use: about 0.1 GB at 8K and 0.0 GB at 512.

Where can I download T5 Small GGUF?

The files are on Hugging Face in the cahaj/t5-small-awesome-text-to-sql-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 T5 Small 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.

Similar models

Browse all →

More from cahaj

All by cahaj →

More Small models

All Small →

Other tiny models

All tiny models →