ST

starcoder2-3b-instruct

StarCoderGGUF by flyingfishinwaterUpdated 2024-03-07
Download on Hugging Face
Parameters3.03B
Context16K
Layers30
Architecturestarcoder2
Smallest quant3.2 GB
Quick answer

starcoder2-3b-instruct needs about 4.0 GB of memory at Q8_0 (a 3.2 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 2 quants, from 3.2 GB (Q8_0) to 6.1 GB (F16).

starcoder2-3b-instruct is a 3.03B-parameter StarCoder model in GGUF format, quantized by flyingfishinwater. Its trained context length is 16K tokens. The repository has 2 quant files, from 3.2 GB (Q8_0) to 6.1 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q8_03.2 GB 4.0 GB
Fits Get file →
F166.1 GB 6.8 GB
Fits Get file →

What GPU do you need for starcoder2-3b-instruct?

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 Q8_0 (3.2 GB file, about 4.0 GB in use).
  • 6 GB VRAM: the best quant that fits is Q8_0 (3.2 GB file, about 4.0 GB in use).
  • 8 GB VRAM: the best quant that fits is F16 (6.1 GB file, about 6.8 GB in use).

Which starcoder2-3b-instruct quant should you choose?

Q8_0 (3.2 GB) is the middle option in this repository. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturestarcoder2
Parameters3.03B
Layers30
Trained context16,384 tokens
KV cache (fp16)30 KB per token

Source

Quantized byflyingfishinwater
FamilyStarCoder
Downloads (HF)30
Last updated2024-03-07

Frequently asked questions about starcoder2-3b-instruct

How much VRAM does starcoder2-3b-instruct need?

About 4.0 GB at Q8_0 with an 8K context window. That is the 3.2 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 starcoder2-3b-instruct on an 8 GB GPU?

Yes, with F16: the 6.1 GB file needs about 6.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of starcoder2-3b-instruct GGUF?

It depends on the quant: Q8_0 is 3.2 GB, F16 is 6.1 GB.

What context length does starcoder2-3b-instruct support?

The GGUF header lists a trained context length of 16,384 tokens (16K). The KV cache grows with the context you use: about 0.3 GB at 8K and 0.5 GB at 16K.

Where can I download starcoder2-3b-instruct GGUF?

The files are on Hugging Face in the flyingfishinwater/starcoder2-3b-instruct-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 starcoder2-3b-instruct 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 StarCoder models

All StarCoder →

Other tiny models

All tiny models →