PH

Phi3-MB_16b

PhiGGUF by SSepiolUpdated 2024-06-05
Download on Hugging Face
Parameters3.82B
Context4K
Layers32
Architecturellama
Smallest quant7.6 GB
Quick answer

Phi3-MB_16b 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.

Phi3-MB_16b is a 3.82B-parameter Phi model in GGUF format, quantized by SSepiol. 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 Phi3-MB_16b?

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 Phi3-MB_16b 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 bySSepiol
FamilyPhi
Licenseapache-2.0
Downloads (HF)25
Last updated2024-06-05

Frequently asked questions about Phi3-MB_16b

How much VRAM does Phi3-MB_16b 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 Phi3-MB_16b 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 Phi3-MB_16b GGUF?

It depends on the quant: F16 is 7.6 GB.

What context length does Phi3-MB_16b 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 Phi3-MB_16b GGUF?

The files are on Hugging Face in the SSepiol/Phi3-MB_16b repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Phi3-MB_16b 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.

Other GGUFs of Phi-3-mini-4k-instruct-bnb-4bit

Similar models

Browse all →

More from SSepiol

All by SSepiol →

More Phi models

All Phi →

Other small models

All small models →