PH

phi 2 instruct v1

PhiGGUF by timothycklUpdated 2024-04-12
Download on Hugging Face
Parameters2.78B
Context2K
Layers32
Architecturephi2
Smallest quant1.7 GB
Quick answer

phi 2 instruct v1 needs about 4.9 GB of memory at its main file (a 1.7 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 2 quants, from 1.7 GB to 2.0 GB.

phi 2 instruct v1 is a 2.78B-parameter Phi model in GGUF format, quantized by timothyckl. Its trained context length is 2K tokens. The repository has 2 quant files, from 1.7 GB to 2.0 GB.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—1.7 GB 2.9 GB
Fits Get file →
—2.0 GB 3.2 GB
Fits Get file →

What GPU do you need for phi 2 instruct v1?

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: the best quant that fits is the main file (2.0 GB file, about 5.2 GB in use).

Specifications

Architecture from the GGUF header

Architecturephi2
Parameters2.78B
Layers32
Trained context2,048 tokens
KV cache (fp16)320 KB per token

Source

Quantized bytimothyckl
FamilyPhi
Downloads (HF)29
Last updated2024-04-12

Frequently asked questions about phi 2 instruct v1

How much VRAM does phi 2 instruct v1 need?

About 4.9 GB at its main file with an 8K context window. That is the 1.7 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 instruct v1 on an 8 GB GPU?

Yes, with the smaller files: the 2.0 GB file needs about 5.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of phi 2 instruct v1 GGUF?

It depends on the quant: file is 1.7 GB, file is 2.0 GB.

What context length does phi 2 instruct v1 support?

The GGUF header lists a trained context length of 2,048 tokens (2K). The KV cache grows with the context you use: about 2.7 GB at 8K and 0.7 GB at 2K.

Where can I download phi 2 instruct v1 GGUF?

The files are on Hugging Face in the timothyckl/phi-2-instruct-v1 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 Phi models

All Phi →

Other tiny models

All tiny models →