phi 2 quantized needs about 2.6 GB of memory at its main file (a 1.9 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 3 quants, from 1.6 GB to 3.0 GB.
phi 2 quantized is a 2.78B-parameter Phi model in GGUF format, quantized by radames. The repository has 3 quant files, from 1.6 GB to 3.0 GB.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 1.6 GB | 2.3 GB | Fits | Get file → | |
| — | 1.9 GB | 2.6 GB | Fits | Get file → | |
| — | 3.0 GB | 3.8 GB | Fits | Get file → |
What GPU do you need for phi 2 quantized?
These figures add the file size, an fp16 KV cache at an 8K context window 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: the best quant that fits is the main file (3.0 GB file, about 3.8 GB in use).
Which phi 2 quantized quant should you choose?
If memory is tight, the smallest file is the first one in the table at 1.6 GB, with the quality trade-offs that come with fewer bits.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about phi 2 quantized
How much VRAM does phi 2 quantized need?
About 2.6 GB at its main file with an 8K context window. That is the 1.9 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 phi 2 quantized on an 8 GB GPU?
Yes, with the smaller files: the 3.0 GB file needs about 3.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of phi 2 quantized GGUF?
It depends on the quant: file is 1.6 GB, file is 1.9 GB, file is 3.0 GB.
Where can I download phi 2 quantized GGUF?
The files are on Hugging Face in the radames/phi-2-quantized repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.