ST

Starcoderbase 1b

StarCoderGGUF by wsxiaoysUpdated 2024-09-06
Download on Hugging Face
Parameters1.14B
Context8K
Layers24
Architecturestarcoder
Smallest quant0.5 GB
Quick answer

Starcoderbase 1b needs about 1.1 GB of memory at Q2_K (a 0.5 GB file) with an 8K context window, so it fits on a 4 GB GPU.

Starcoderbase 1b is a 1.14B-parameter StarCoder model in GGUF format, quantized by wsxiaoys. Its trained context length is 8K tokens. The repository has 1 quant file, from 0.5 GB (Q2_K) to 0.5 GB (Q2_K).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K0.5 GB 1.1 GB
Fits Get file →

What GPU do you need for Starcoderbase 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 Q2_K (0.5 GB file, about 1.1 GB in use).

Which Starcoderbase 1b quant should you choose?

Q2_K (0.5 GB) is the middle option in this repository. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturestarcoder
Parameters1.14B
Layers24
Trained context8,192 tokens
KV cache (fp16)12 KB per token

Source

Quantized bywsxiaoys
FamilyStarCoder
Downloads (HF)16
Last updated2024-09-06

Frequently asked questions about Starcoderbase 1b

How much VRAM does Starcoderbase 1b need?

About 1.1 GB at Q2_K with an 8K context window. That is the 0.5 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 Starcoderbase 1b on an 8 GB GPU?

Yes, with Q2_K: the 0.5 GB file needs about 1.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Starcoderbase 1b GGUF?

It depends on the quant: Q2_K is 0.5 GB.

What context length does Starcoderbase 1b support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 0.1 GB at 8K and 0.1 GB at 8K.

Where can I download Starcoderbase 1b GGUF?

The files are on Hugging Face in the wsxiaoys/starcoderbase-1b-Q2_K-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 Starcoderbase 1b use?

Hugging Face lists the license as bigcode-openrail-m. 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 wsxiaoys

All by wsxiaoys →

More StarCoder models

All StarCoder →

Other tiny models

All tiny models →