PH

Phi 3.5 Hyper Mix IQ4 XS

PhiGGUF by bunnycoreUpdated 2024-09-27
Download on Hugging Face
Parameters3.82B
Context128K
Layers32
Architecturephi3
Smallest quant2.1 GB
Quick answer

Phi 3.5 Hyper Mix IQ4 XS needs about 5.8 GB of memory at IQ4_XS (a 2.1 GB file) with an 8K context window, so it fits on a 6 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 12.9 GB.

Phi 3.5 Hyper Mix IQ4 XS is a 3.82B-parameter Phi model in GGUF format, quantized by bunnycore. Its trained context length is 128K tokens. The repository has 1 quant file, from 2.1 GB (IQ4_XS) to 2.1 GB (IQ4_XS).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ4_XS2.1 GB 5.8 GB
Fits Get file →

What GPU do you need for Phi 3.5 Hyper Mix IQ4 XS?

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 IQ4_XS (2.1 GB file, about 5.8 GB in use).

Which Phi 3.5 Hyper Mix IQ4 XS quant should you choose?

IQ4_XS (2.1 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

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

Source

Quantized bybunnycore
FamilyPhi
Downloads (HF)106
Last updated2024-09-27

Frequently asked questions about Phi 3.5 Hyper Mix IQ4 XS

How much VRAM does Phi 3.5 Hyper Mix IQ4 XS need?

About 5.8 GB at IQ4_XS with an 8K context window. That is the 2.1 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 3.5 Hyper Mix IQ4 XS on an 8 GB GPU?

Yes, with IQ4_XS: the 2.1 GB file needs about 5.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Phi 3.5 Hyper Mix IQ4 XS GGUF?

It depends on the quant: IQ4_XS is 2.1 GB.

What context length does Phi 3.5 Hyper Mix IQ4 XS 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 Phi 3.5 Hyper Mix IQ4 XS GGUF?

The files are on Hugging Face in the bunnycore/Phi-3.5-Hyper-Mix-IQ4_XS-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Other GGUFs of Phi-3.5-Hyper-Mix

Similar models

Browse all →

More from bunnycore

All by bunnycore →

More Phi models

All Phi →

Other small models

All small models →