ST

Codefuse Starcoder2 15b

StarCoderGGUF by NekuromentoUpdated 2024-08-16
Download on Hugging Face
Parameters16B
Context16K
Layers40
Architecturestarcoder2
Smallest quant13.1 GB
Quick answer

Codefuse Starcoder2 15b needs about 14.3 GB of memory at Q6_K (a 13.1 GB file) with an 8K context window, so it fits on a 16 GB GPU.

Codefuse Starcoder2 15b is a 16B-parameter StarCoder model in GGUF format, quantized by Nekuromento. Its trained context length is 16K tokens. The repository has 1 quant file, from 13.1 GB (Q6_K) to 13.1 GB (Q6_K).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q6_K13.1 GB 14.3 GB
Too big Get file →

What GPU do you need for Codefuse Starcoder2 15b?

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: no quant fits at an 8K context.
  • 16 GB VRAM: the best quant that fits is Q6_K (13.1 GB file, about 14.3 GB in use).

Which Codefuse Starcoder2 15b quant should you choose?

Q6_K (13.1 GB) is the middle option in this repository. Very close to the original quality for most uses, at a clearly larger size than 4-bit.

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 byNekuromento
FamilyStarCoder
Downloads (HF)31
Last updated2024-08-16

Frequently asked questions about Codefuse Starcoder2 15b

How much VRAM does Codefuse Starcoder2 15b need?

About 14.3 GB at Q6_K with an 8K context window. That is the 13.1 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 Codefuse Starcoder2 15b on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 14.3 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Codefuse Starcoder2 15b GGUF?

It depends on the quant: Q6_K is 13.1 GB.

What context length does Codefuse Starcoder2 15b 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 Codefuse Starcoder2 15b GGUF?

The files are on Hugging Face in the Nekuromento/CodeFuse-StarCoder2-15B-Q6_K-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Other GGUFs of CodeFuse-StarCoder2-15B

Similar models

Browse all →

More from Nekuromento

All by Nekuromento →

More StarCoder models

All StarCoder →

Other medium models

All medium models →