BA

T5 Base

BaseGGUF by FelladrinUpdated 2024-07-26
Download on Hugging Face
Parameters248M
Context512
Layers12
Architecturet5
Smallest quant0.2 GB
Quick answer

T5 Base needs about 1.0 GB of memory at Q6_K (a 0.2 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 5 quants, from 0.2 GB (IQ4_XS) to 0.5 GB.

T5 Base is a 248M-parameter Base model in GGUF format, quantized by Felladrin. Its trained context length is 512 tokens. The repository has 5 quant files, from 0.2 GB (IQ4_XS) to 0.5 GB.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ4_XS0.2 GB 0.7 GB
Fits Get file →
Q5_K0.2 GB 0.7 GB
Fits Get file →
Q6_K0.2 GB 0.7 GB
Fits Get file →
Q8_00.3 GB 0.8 GB
Fits Get file →
—0.5 GB 1.0 GB
Fits Get file →

What GPU do you need for T5 Base?

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 the main file (0.5 GB file, about 1.3 GB in use).

Which T5 Base quant should you choose?

Q6_K (0.2 GB) is the middle option in this repository. Very close to the original quality for most uses, at a clearly larger size than 4-bit.

If memory is tight, the smallest file is IQ4_XS at 0.2 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

Architecturet5
Parameters248M
Layers12
Trained context512 tokens
KV cache (fp16)36 KB per token

Source

Quantized byFelladrin
FamilyBase
Downloads (HF)80
Last updated2024-07-26

Frequently asked questions about T5 Base

How much VRAM does T5 Base need?

About 1.0 GB at Q6_K 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 Base on an 8 GB GPU?

Yes, with the smaller files: the 0.5 GB file needs about 1.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of T5 Base GGUF?

It depends on the quant: IQ4_XS is 0.2 GB, Q5_K is 0.2 GB, Q6_K is 0.2 GB, Q8_0 is 0.3 GB, file is 0.5 GB.

What context length does T5 Base support?

The GGUF header lists a trained context length of 512 tokens (512). The KV cache grows with the context you use: about 0.3 GB at 8K and 0.0 GB at 512.

Where can I download T5 Base GGUF?

The files are on Hugging Face in the Felladrin/gguf-t5-base-grammar-correction 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 Base use?

Hugging Face lists the license as cc-by-nc-sa-4.0. 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 Felladrin

All by Felladrin →

More Base models

All Base →

Other tiny models

All tiny models →