Phil 18B Il1 needs about 13.7 GB of memory at Q4_K_M (a 11.1 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 3 quants, from 10.3 GB (Q4_0) to 19.2 GB (Q8_0).
Phil 18B Il1 is a 18.1B-parameter Phil model in GGUF format, quantized by altomek. Its trained context length is 16K tokens. The repository has 3 quant files, from 10.3 GB (Q4_0) to 19.2 GB (Q8_0).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_0 | 10.3 GB | 12.9 GB | Too big | Get file → | |
| Q4_K_M | 11.1 GB | 13.7 GB | Too big | Get file → | |
| Q8_0 | 19.2 GB | 21.8 GB | Too big | Get file → |
What GPU do you need for Phil 18B Il1?
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 Q4_K_M (11.1 GB file, about 13.7 GB in use).
- 24 GB VRAM: the best quant that fits is Q8_0 (19.2 GB file, about 21.8 GB in use).
Which Phil 18B Il1 quant should you choose?
Q4_K_M is the usual starting point for Phil 18B Il1: it balances file size and quality well. Here it is a 11.1 GB file.
The Q8_0 file is 19.2 GB, about 1.7 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.
If memory is tight, the smallest file is Q4_0 at 10.3 GB, with the quality trade-offs that come with fewer bits. 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 Phil 18B Il1
How much VRAM does Phil 18B Il1 need?
About 13.7 GB at Q4_K_M with an 8K context window. That is the 11.1 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 Phil 18B Il1 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 12.9 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Phil 18B Il1 GGUF?
It depends on the quant: Q4_0 is 10.3 GB, Q4_K_M is 11.1 GB, Q8_0 is 19.2 GB.
What context length does Phil 18B Il1 support?
The GGUF header lists a trained context length of 16,384 tokens (16K). The KV cache grows with the context you use: about 2.1 GB at 8K and 4.2 GB at 16K.
Where can I download Phil 18B Il1 GGUF?
The files are on Hugging Face in the altomek/Phil-18B-il1-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 Phil 18B Il1 use?
Hugging Face lists the license as mit. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.