ST

starcoder2-15b-instruct

StarCoderGGUF by LapinMalinUpdated 2024-03-07
Download on Hugging Face
Parameters16B
Context16K
Layers40
Architecturestarcoder2
Smallest quant8.1 GB
Quick answer

starcoder2-15b-instruct needs about 11.0 GB of memory at Q4_K_M (a 9.9 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 2 quants, from 8.1 GB (Q3_K_M) to 9.9 GB (Q4_K_M).

starcoder2-15b-instruct is a 16B-parameter StarCoder model in GGUF format, quantized by LapinMalin. Its trained context length is 16K tokens. The repository has 2 quant files, from 8.1 GB (Q3_K_M) to 9.9 GB (Q4_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q3_K_M8.1 GB 9.3 GB
Too big Get file →
Q4_K_M9.9 GB 11.0 GB
Too big Get file →

What GPU do you need for starcoder2-15b-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: no quant fits at an 8K context.
  • 6 GB VRAM: no quant fits at an 8K context.
  • 8 GB VRAM: no quant fits at an 8K context.
  • 12 GB VRAM: the best quant that fits is Q4_K_M (9.9 GB file, about 11.0 GB in use).

Which starcoder2-15b-instruct quant should you choose?

Q4_K_M is the usual starting point for starcoder2-15b-instruct: it balances file size and quality well. Here it is a 9.9 GB file.

If memory is tight, the smallest file is Q3_K_M at 8.1 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturestarcoder2
Parameters16B
Layers40
Trained context16,384 tokens
KV cache (fp16)80 KB per token

Source

Quantized byLapinMalin
FamilyStarCoder
Downloads (HF)83
Last updated2024-03-07

Frequently asked questions about starcoder2-15b-instruct

How much VRAM does starcoder2-15b-instruct need?

About 11.0 GB at Q4_K_M with an 8K context window. That is the 9.9 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 starcoder2-15b-instruct on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 9.3 GB, so you would need a larger GPU or CPU offloading.

What is the file size of starcoder2-15b-instruct GGUF?

It depends on the quant: Q3_K_M is 8.1 GB, Q4_K_M is 9.9 GB.

What context length does starcoder2-15b-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 0.7 GB at 8K and 1.3 GB at 16K.

Where can I download starcoder2-15b-instruct GGUF?

The files are on Hugging Face in the LapinMalin/starcoder2-15b-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 starcoder2-15b-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 from LapinMalin

All by LapinMalin →

More StarCoder models

All StarCoder →

Other medium models

All medium models →