Darwin 28B Coder needs about 16.5 GB of memory at its main file (a 13.9 GB file) with an 8K context window, so it fits on a 24 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 8.6 GB.
Darwin 28B Coder is a 26.9B-parameter Darwin model in GGUF format, quantized by k0valik. Its trained context length is 256K tokens. The repository has 1 quant file, from 13.9 GB to 13.9 GB.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 13.9 GB | 16.5 GB | Too big | Get file → |
What GPU do you need for Darwin 28B Coder?
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: no quant fits at an 8K context.
- 24 GB VRAM: the best quant that fits is the main file (13.9 GB file, about 16.5 GB in use).
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Darwin 28B Coder
How much VRAM does Darwin 28B Coder need?
About 16.5 GB at its main file with an 8K context window. That is the 13.9 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 Darwin 28B Coder on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 16.5 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Darwin 28B Coder GGUF?
It depends on the quant: file is 13.9 GB.
What context length does Darwin 28B Coder support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 2.1 GB at 8K and 8.6 GB at 32K.
Where can I download Darwin 28B Coder GGUF?
The files are on Hugging Face in the k0valik/Darwin-28B-Coder-IQ4_XS12.9GiB-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 Darwin 28B Coder use?
Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.