starcoder2-15b-instruct needs about 11.0 GB of memory at Q4_K (a 9.9 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 6 quants, from 6.7 GB (IQ3_XS) to 17.0 GB (Q8_0).
starcoder2-15b-instruct is a 16B-parameter StarCoder model in GGUF format, quantized by dranger003. Its trained context length is 16K tokens. The repository has 6 quant files, from 6.7 GB (IQ3_XS) to 17.0 GB (Q8_0).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ3_XS | 6.7 GB | 7.9 GB | Tight | Get file → | |
| IQ4_XS | 8.6 GB | 9.8 GB | Too big | Get file → | |
| Q4_K | 9.9 GB | 11.0 GB | Too big | Get file → | |
| Q5_K | 11.4 GB | 12.6 GB | Too big | Get file → | |
| Q6_K | 13.1 GB | 14.3 GB | Too big | Get file → | |
| Q8_0 | 17.0 GB | 18.1 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: the best quant that fits is IQ3_XS (6.7 GB file, about 7.9 GB in use).
- 12 GB VRAM: the best quant that fits is Q4_K (9.9 GB file, about 11.0 GB in use).
- 16 GB VRAM: the best quant that fits is Q6_K (13.1 GB file, about 14.3 GB in use).
- 24 GB VRAM: the best quant that fits is Q8_0 (17.0 GB file, about 18.1 GB in use).
Which starcoder2-15b-instruct quant should you choose?
Q4_K (9.9 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.
If memory is tight, the smallest file is IQ3_XS at 6.7 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
Source
Frequently asked questions about starcoder2-15b-instruct
How much VRAM does starcoder2-15b-instruct need?
About 11.0 GB at Q4_K 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?
Yes, with IQ3_XS: the 6.7 GB file needs about 7.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of starcoder2-15b-instruct GGUF?
It depends on the quant: IQ3_XS is 6.7 GB, IQ4_XS is 8.6 GB, Q4_K is 9.9 GB, Q5_K is 11.4 GB, Q6_K is 13.1 GB, Q8_0 is 17.0 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 dranger003/starcoder2-15b-instruct-iMat.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.