CO

code t5

CodeGGUF by JinendraUpdated 2024-07-20
Download on Hugging Face
Parameters223M
Context—
Layers—
Architecture—
Smallest quant0.2 GB
Quick answer

code t5 needs about 0.7 GB of memory at its main file (a 0.2 GB file) with an 8K context window, so it fits on a 4 GB GPU.

code t5 is a 223M-parameter Code model in GGUF format, quantized by Jinendra. The repository has 1 quant file, from 0.2 GB to 0.2 GB.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.2 GB 0.7 GB
Fits Get file →

What GPU do you need for code t5?

These figures add the file size, an fp16 KV cache at an 8K context window 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 (0.2 GB file, about 0.7 GB in use).

Specifications

Architecture from the GGUF header

Parameters223M

Source

Quantized byJinendra
FamilyCode
Downloads (HF)67
Last updated2024-07-20

Frequently asked questions about code t5

How much VRAM does code t5 need?

About 0.7 GB at its main file 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 code t5 on an 8 GB GPU?

Yes, with the smaller files: the 0.2 GB file needs about 0.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of code t5 GGUF?

It depends on the quant: file is 0.2 GB.

Where can I download code t5 GGUF?

The files are on Hugging Face in the Jinendra/code-t5 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 Code models

All Code →

Other tiny models

All tiny models →