PH

phi3 ft

PhiGGUF by AnishproshortUpdated 2024-07-15
Download on Hugging Face
Parameters3.82B
Context128K
Layers32
Architecturephi3
Smallest quant2.8 GB
Quick answer

phi3 ft needs about 6.5 GB of memory at its main file (a 2.8 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 2 quants, from 2.8 GB to 7.6 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 12.9 GB.

phi3 ft is a 3.82B-parameter Phi model in GGUF format, quantized by Anishproshort. Its trained context length is 128K tokens. The repository has 2 quant files, from 2.8 GB to 7.6 GB.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—2.8 GB 6.5 GB
Fits Get file →
—7.6 GB 11.4 GB
Too big Get file →

What GPU do you need for phi3 ft?

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: the best quant that fits is the main file (2.8 GB file, about 6.5 GB in use).
  • 12 GB VRAM: the best quant that fits is the main file (7.6 GB file, about 11.4 GB in use).

Specifications

Architecture from the GGUF header

Architecturephi3
Parameters3.82B
Layers32
Trained context131,072 tokens
KV cache (fp16)384 KB per token

Source

Quantized byAnishproshort
FamilyPhi
Downloads (HF)5
Last updated2024-07-15

Frequently asked questions about phi3 ft

How much VRAM does phi3 ft need?

About 6.5 GB at its main file with an 8K context window. That is the 2.8 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 phi3 ft on an 8 GB GPU?

Yes, with the smaller files: the 2.8 GB file needs about 6.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of phi3 ft GGUF?

It depends on the quant: file is 2.8 GB, file is 7.6 GB.

What context length does phi3 ft support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 3.2 GB at 8K and 12.9 GB at 32K.

Where can I download phi3 ft GGUF?

The files are on Hugging Face in the Anishproshort/phi3_ft 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 Anishproshort

All by Anishproshort →

More Phi models

All Phi →

Other small models

All small models →