PH

phi 2 imatrix

PhiGGUF by ristewUpdated 2024-02-16
Download on Hugging Face
Parameters2.78B
Context2K
Layers32
Architecturephi2
Smallest quant0.7 GB
Quick answer

phi 2 imatrix needs about 4.0 GB of memory at IQ2_XXS (a 0.8 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 4 quants, from 0.7 GB (IQ1_S) to 1.2 GB (IQ3_XXS).

phi 2 imatrix is a 2.78B-parameter Phi model in GGUF format, quantized by ristew. Its trained context length is 2K tokens. The repository has 4 quant files, from 0.7 GB (IQ1_S) to 1.2 GB (IQ3_XXS).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S0.7 GB 1.9 GB
Fits Get file →
IQ2_XXS0.8 GB 2.0 GB
Fits Get file →
IQ2_XS0.9 GB 2.1 GB
Fits Get file →
IQ3_XXS1.2 GB 2.3 GB
Fits Get file →

What GPU do you need for phi 2 imatrix?

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: the best quant that fits is IQ2_XXS (0.8 GB file, about 4.0 GB in use).
  • 6 GB VRAM: the best quant that fits is IQ3_XXS (1.2 GB file, about 4.3 GB in use).

Which phi 2 imatrix quant should you choose?

IQ2_XXS (0.8 GB) is the middle option in this repository. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

If memory is tight, the smallest file is IQ1_S at 0.7 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

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 byristew
FamilyPhi
Downloads (HF)66
Last updated2024-02-16

Frequently asked questions about phi 2 imatrix

How much VRAM does phi 2 imatrix need?

About 4.0 GB at IQ2_XXS 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 phi 2 imatrix on an 8 GB GPU?

Yes, with IQ3_XXS: the 1.2 GB file needs about 4.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of phi 2 imatrix GGUF?

It depends on the quant: IQ1_S is 0.7 GB, IQ2_XXS is 0.8 GB, IQ2_XS is 0.9 GB, IQ3_XXS is 1.2 GB.

What context length does phi 2 imatrix 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 imatrix GGUF?

The files are on Hugging Face in the ristew/phi-2-imatrix-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 Phi models

All Phi →

Other tiny models

All tiny models →