PH

Demo Phi3 instructionMachine 16bit

PhiGGUF by PeerapolUpdated 2024-07-31
Download on Hugging Face
Parameters3.82B
Context4K
Layers32
Architecturellama
Smallest quant7.6 GB
Quick answer

Demo Phi3 instructionMachine 16bit needs about 11.4 GB of memory at F16 (a 7.6 GB file) with an 8K context window, so it fits on a 12 GB GPU.

Demo Phi3 instructionMachine 16bit is a 3.82B-parameter Phi model in GGUF format, quantized by Peerapol. Its trained context length is 4K tokens. The repository has 1 quant file, from 7.6 GB (F16) to 7.6 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
F167.6 GB 9.8 GB
Too big Get file →

What GPU do you need for Demo Phi3 instructionMachine 16bit?

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: no quant fits at an 8K context.
  • 12 GB VRAM: the best quant that fits is F16 (7.6 GB file, about 11.4 GB in use).

Which Demo Phi3 instructionMachine 16bit quant should you choose?

F16 (7.6 GB) is the middle option in this repository. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters3.82B
Layers32
Trained context4,096 tokens
KV cache (fp16)384 KB per token

Source

Quantized byPeerapol
FamilyPhi
Licenseapache-2.0
Downloads (HF)12
Last updated2024-07-31

Frequently asked questions about Demo Phi3 instructionMachine 16bit

How much VRAM does Demo Phi3 instructionMachine 16bit need?

About 11.4 GB at F16 with an 8K context window. That is the 7.6 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 Demo Phi3 instructionMachine 16bit on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 11.4 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Demo Phi3 instructionMachine 16bit GGUF?

It depends on the quant: F16 is 7.6 GB.

What context length does Demo Phi3 instructionMachine 16bit support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 3.2 GB at 8K and 1.6 GB at 4K.

Where can I download Demo Phi3 instructionMachine 16bit GGUF?

The files are on Hugging Face in the Peerapol/Demo_Phi3_instructionMachine_16bit_GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Demo Phi3 instructionMachine 16bit use?

Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Similar models

Browse all →

More from Peerapol

All by Peerapol →

More Phi models

All Phi →

Other small models

All small models →