ST

starcoder2

StarCoderGGUF by MooizzUpdated 2024-05-07
Download on Hugging Face
Parameters7.17B
Context16K
Layers32
Architecturestarcoder2
Smallest quant4.1 GB
Quick answer

starcoder2 needs about 5.5 GB of memory at Q4_K_M (a 4.5 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 3 quants, from 4.1 GB (Q4_K_S) to 14.4 GB (F16).

starcoder2 is a 7.17B-parameter StarCoder model in GGUF format, quantized by Mooizz. Its trained context length is 16K tokens. The repository has 3 quant files, from 4.1 GB (Q4_K_S) to 14.4 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_S4.1 GB 5.2 GB
Fits Get file →
Q4_K_M4.5 GB 5.5 GB
Fits Get file →
F1614.4 GB 15.4 GB
Too big Get file →

What GPU do you need for starcoder2?

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: no quant fits at an 8K context.
  • 6 GB VRAM: the best quant that fits is Q4_K_M (4.5 GB file, about 5.5 GB in use).
  • 8 GB VRAM: the best quant that fits is Q4_K_M (4.5 GB file, about 5.5 GB in use).
  • 12 GB VRAM: the best quant that fits is Q4_K_M (4.5 GB file, about 5.5 GB in use).
  • 16 GB VRAM: the best quant that fits is F16 (14.4 GB file, about 15.4 GB in use).

Which starcoder2 quant should you choose?

Q4_K_M is the usual starting point for starcoder2: it balances file size and quality well. Here it is a 4.5 GB file.

If memory is tight, the smallest file is Q4_K_S at 4.1 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

Architecturestarcoder2
Parameters7.17B
Layers32
Trained context16,384 tokens
KV cache (fp16)64 KB per token

Source

Quantized byMooizz
FamilyStarCoder
Licensemit
Downloads (HF)110
Last updated2024-05-07

Frequently asked questions about starcoder2

How much VRAM does starcoder2 need?

About 5.5 GB at Q4_K_M with an 8K context window. That is the 4.5 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 starcoder2 on an 8 GB GPU?

Yes, with Q4_K_M: the 4.5 GB file needs about 5.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of starcoder2 GGUF?

It depends on the quant: Q4_K_S is 4.1 GB, Q4_K_M is 4.5 GB, F16 is 14.4 GB.

What context length does starcoder2 support?

The GGUF header lists a trained context length of 16,384 tokens (16K). The KV cache grows with the context you use: about 0.5 GB at 8K and 1.1 GB at 16K.

Where can I download starcoder2 GGUF?

The files are on Hugging Face in the Mooizz/starcoder2-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 use?

Hugging Face lists the license as mit. 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 small models

All small models →