starcoder2-15b needs about 10.2 GB of memory at Q4_0 (a 9.1 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 2 quants, from 9.1 GB (Q4_0) to 11.4 GB (Q5_K_M).
starcoder2-15b is a 16B-parameter StarCoder model in GGUF format, quantized by hbacard. Its trained context length is 16K tokens. The repository has 2 quant files, from 9.1 GB (Q4_0) to 11.4 GB (Q5_K_M).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_0 | 9.1 GB | 10.2 GB | Too big | Get file → | |
| Q5_K_M | 11.4 GB | 12.6 GB | Too big | Get file → |
What GPU do you need for 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: the best quant that fits is Q4_0 (9.1 GB file, about 10.2 GB in use).
- 16 GB VRAM: the best quant that fits is Q5_K_M (11.4 GB file, about 12.6 GB in use).
Which starcoder2-15b quant should you choose?
Q4_0 (9.1 GB) is the middle option in this repository. 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
Source
Frequently asked questions about starcoder2-15b
How much VRAM does starcoder2-15b need?
About 10.2 GB at Q4_0 with an 8K context window. That is the 9.1 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 starcoder2-15b on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 10.2 GB, so you would need a larger GPU or CPU offloading.
What is the file size of starcoder2-15b GGUF?
It depends on the quant: Q4_0 is 9.1 GB, Q5_K_M is 11.4 GB.
What context length does 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 starcoder2-15b GGUF?
The files are on Hugging Face in the hbacard/starcoder2-15b-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.