PH

Candle phi 2

PhiGGUF by DanielCloughUpdated 2024-01-26
Download on Hugging Face
Parameters2.78B
Context—
Layers—
Architecture—
Smallest quant0.9 GB
Quick answer

Candle phi 2 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 13 quants, from 0.9 GB to 5.6 GB (F16).

Candle phi 2 is a 2.78B-parameter Phi model in GGUF format, quantized by DanielClough. The repository has 13 quant files, from 0.9 GB to 5.6 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.9 GB 1.5 GB
Fits Get file →
—1.2 GB 1.8 GB
Fits Get file →
Q4_01.6 GB 2.3 GB
Fits Get file →
—1.6 GB 2.3 GB
Fits Get file →
Q4_11.7 GB 2.4 GB
Fits Get file →
Q5_01.9 GB 2.6 GB
Fits Get file →
—1.9 GB 2.6 GB
Fits Get file →
Q5_12.1 GB 2.8 GB
Fits Get file →
—2.3 GB 3.1 GB
Fits Get file →
Q8_03.0 GB 3.8 GB
Fits Get file →
Q8_13.1 GB 4.0 GB
Fits Get file →
—3.2 GB 4.1 GB
Fits Get file →
F165.6 GB 6.7 GB
Fits Get file →

What GPU do you need for Candle phi 2?

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 Q8_1 (3.1 GB file, about 4.0 GB in use).
  • 6 GB VRAM: the best quant that fits is the main file (3.2 GB file, about 4.1 GB in use).
  • 8 GB VRAM: the best quant that fits is F16 (5.6 GB file, about 6.7 GB in use).

Which Candle phi 2 quant should you choose?

If memory is tight, the smallest file is the first one in the table at 0.9 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

Parameters2.78B

Source

Quantized byDanielClough
FamilyPhi
Licensemit
Downloads (HF)107
Last updated2024-01-26

Frequently asked questions about Candle phi 2

How much VRAM does Candle phi 2 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 Candle phi 2 on an 8 GB GPU?

Yes, with F16: the 5.6 GB file needs about 6.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Candle phi 2 GGUF?

It depends on the quant: file is 0.9 GB, file is 1.2 GB, Q4_0 is 1.6 GB, file is 1.6 GB, Q4_1 is 1.7 GB, Q5_0 is 1.9 GB and 7 more.

Where can I download Candle phi 2 GGUF?

The files are on Hugging Face in the DanielClough/Candle_phi-2 repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Candle phi 2 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.

Similar models

Browse all →

More from DanielClough

All by DanielClough →

More Phi models

All Phi →

Other tiny models

All tiny models →