PH

op phi 1.5

PhiGGUF by operator-technologyUpdated 2024-04-02
Download on Hugging Face
Parameters1.41B
Context—
Layers—
Architecture—
Smallest quant0.8 GB
Quick answer

op phi 1.5 needs about 1.4 GB of memory at its main file (a 0.8 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 2 quants, from 0.8 GB to 2.8 GB (F16).

op phi 1.5 is a 1.41B-parameter Phi model in GGUF format, quantized by operator-technology. The repository has 2 quant files, from 0.8 GB to 2.8 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.8 GB 1.4 GB
Fits Get file →
F162.8 GB 3.7 GB
Fits Get file →

What GPU do you need for op phi 1.5?

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 F16 (2.8 GB file, about 3.7 GB in use).

Specifications

Architecture from the GGUF header

Parameters1.41B

Source

FamilyPhi
Downloads (HF)40
Last updated2024-04-02

Frequently asked questions about op phi 1.5

How much VRAM does op phi 1.5 need?

About 1.4 GB at its main file with an 8K context window. That is the 0.8 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 op phi 1.5 on an 8 GB GPU?

Yes, with F16: the 2.8 GB file needs about 3.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of op phi 1.5 GGUF?

It depends on the quant: file is 0.8 GB, F16 is 2.8 GB.

Where can I download op phi 1.5 GGUF?

The files are on Hugging Face in the operator-technology/op-phi-1.5-gguf repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Similar models

Browse all →

More from operator-technology

All by operator-technology →

More Phi models

All Phi →

Other tiny models

All tiny models →