SA

SantaCoder 1B

SantacoderGGUF by guinmoonUpdated 2023-10-18
Download on Hugging Face
Parameters1.23B
Context2K
Layers24
Architecturestarcoder
Smallest quant0.9 GB
Quick answer

SantaCoder 1B needs about 1.5 GB of memory at Q5_K (a 0.9 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 2 quants, from 0.9 GB (Q5_K) to 2.5 GB (F16).

SantaCoder 1B is a 1.23B-parameter Santacoder model in GGUF format, quantized by guinmoon. Its trained context length is 2K tokens. The repository has 2 quant files, from 0.9 GB (Q5_K) to 2.5 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q5_K0.9 GB 1.4 GB
Fits Get file →
F162.5 GB 3.0 GB
Fits Get file →

What GPU do you need for SantaCoder 1B?

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 (2.5 GB file, about 3.1 GB in use).

Which SantaCoder 1B quant should you choose?

Q5_K (0.9 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

Architecturestarcoder
Parameters1.23B
Layers24
Trained context2,048 tokens
KV cache (fp16)12 KB per token

Source

Quantized byguinmoon
Downloads (HF)74
Last updated2023-10-18

Frequently asked questions about SantaCoder 1B

How much VRAM does SantaCoder 1B need?

About 1.5 GB at Q5_K with an 8K context window. That is the 0.9 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 SantaCoder 1B on an 8 GB GPU?

Yes, with F16: the 2.5 GB file needs about 3.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of SantaCoder 1B GGUF?

It depends on the quant: Q5_K is 0.9 GB, F16 is 2.5 GB.

What context length does SantaCoder 1B support?

The GGUF header lists a trained context length of 2,048 tokens (2K). The KV cache grows with the context you use: about 0.1 GB at 8K and 0.0 GB at 2K.

Where can I download SantaCoder 1B GGUF?

The files are on Hugging Face in the guinmoon/SantaCoder-1B-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 guinmoon

All by guinmoon →

Other tiny models

All tiny models →