PH

phi 3 8bit Q16 0 gg

PhiGGUF by LeonardLangsdorfUpdated 2024-08-20
Download on Hugging Face
Parameters3.82B
Context4K
Layers32
Architecturellama
Smallest quant7.6 GB
Quick answer

phi 3 8bit Q16 0 gg 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.

phi 3 8bit Q16 0 gg is a 3.82B-parameter Phi model in GGUF format, quantized by LeonardLangsdorf. 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 phi 3 8bit Q16 0 gg?

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 phi 3 8bit Q16 0 gg 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 byLeonardLangsdorf
FamilyPhi
Licenseapache-2.0
Downloads (HF)26
Last updated2024-08-20

Frequently asked questions about phi 3 8bit Q16 0 gg

How much VRAM does phi 3 8bit Q16 0 gg 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 phi 3 8bit Q16 0 gg 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 phi 3 8bit Q16 0 gg GGUF?

It depends on the quant: F16 is 7.6 GB.

What context length does phi 3 8bit Q16 0 gg 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 phi 3 8bit Q16 0 gg GGUF?

The files are on Hugging Face in the LeonardLangsdorf/phi-3-8bit_Q16_0_gg repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does phi 3 8bit Q16 0 gg 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 LeonardLangsdorf

All by LeonardLangsdorf →

More Phi models

All Phi →

Other small models

All small models →