PH

phi-3-mini-4k-f16

PhiGGUF by ironlanderlUpdated 2024-07-02
Download on Hugging Face
Parameters3.82B
Context4K
Layers32
Architecturellama
Smallest quant2.7 GB
Quick answer

phi-3-mini-4k-f16 needs about 6.4 GB of memory at F16 (a 2.7 GB file) with an 8K context window, so it fits on a 8 GB GPU.

phi-3-mini-4k-f16 is a 3.82B-parameter Phi model in GGUF format, quantized by ironlanderl. Its trained context length is 4K tokens. The repository has 1 quant file, from 2.7 GB (F16) to 2.7 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
F162.7 GB 4.8 GB
Fits Get file →

What GPU do you need for phi-3-mini-4k-f16?

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: the best quant that fits is F16 (2.7 GB file, about 6.4 GB in use).

Which phi-3-mini-4k-f16 quant should you choose?

F16 (2.7 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 byironlanderl
FamilyPhi
Downloads (HF)6
Last updated2024-07-02

Frequently asked questions about phi-3-mini-4k-f16

How much VRAM does phi-3-mini-4k-f16 need?

About 6.4 GB at F16 with an 8K context window. That is the 2.7 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-mini-4k-f16 on an 8 GB GPU?

Yes, with F16: the 2.7 GB file needs about 6.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of phi-3-mini-4k-f16 GGUF?

It depends on the quant: F16 is 2.7 GB.

What context length does phi-3-mini-4k-f16 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-mini-4k-f16 GGUF?

The files are on Hugging Face in the ironlanderl/phi-3-mini-4k-f16-Q5_K_M-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 from ironlanderl

All by ironlanderl →

More Phi models

All Phi →

Other small models

All small models →