PH

phi2 bunny

PhiGGUF by justinj92Updated 2024-01-30
Download on Hugging Face
Parameters2.78B
Context2K
Layers32
Architecturephi2
Smallest quant1.7 GB
Quick answer

phi2 bunny needs about 4.9 GB of memory at Q4_K_M (a 1.7 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 3 quants, from 1.7 GB (Q4_K_M) to 3.0 GB (Q8_0).

phi2 bunny is a 2.78B-parameter Phi model in GGUF format, quantized by justinj92. Its trained context length is 2K tokens. The repository has 3 quant files, from 1.7 GB (Q4_K_M) to 3.0 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M1.7 GB 2.9 GB
Fits Get file →
Q5_K_M2.0 GB 3.2 GB
Fits Get file →
Q8_03.0 GB 4.1 GB
Fits Get file →

What GPU do you need for phi2 bunny?

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 Q5_K_M (2.0 GB file, about 5.2 GB in use).
  • 8 GB VRAM: the best quant that fits is Q8_0 (3.0 GB file, about 6.1 GB in use).

Which phi2 bunny quant should you choose?

Q4_K_M is the usual starting point for phi2 bunny: it balances file size and quality well. Here it is a 1.7 GB file.

The Q8_0 file is 3.0 GB, about 1.7 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

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

Source

Quantized byjustinj92
FamilyPhi
Base modelmicrosoft/phi-2
Licensemit
Downloads (HF)128
Last updated2024-01-30

Frequently asked questions about phi2 bunny

How much VRAM does phi2 bunny need?

About 4.9 GB at Q4_K_M 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 phi2 bunny on an 8 GB GPU?

Yes, with Q8_0: the 3.0 GB file needs about 6.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of phi2 bunny GGUF?

It depends on the quant: Q4_K_M is 1.7 GB, Q5_K_M is 2.0 GB, Q8_0 is 3.0 GB.

What context length does phi2 bunny 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 phi2 bunny GGUF?

The files are on Hugging Face in the justinj92/phi2-bunny repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does phi2 bunny 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.

Other GGUFs of phi-2

Similar models

Browse all →

More from justinj92

All by justinj92 →

More Phi models

All Phi →

Other tiny models

All tiny models →