PH

Phi 3 mini 4k base

PhiGGUF by DeeokayUpdated 2024-07-21
Download on Hugging Face
Parameters3.82B
Context4K
Layers32
Architecturellama
Smallest quant1.9 GB
Quick answer

Phi 3 mini 4k base needs about 6.0 GB of memory at Q4_K_M (a 2.3 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 4 quants, from 1.9 GB (Q3_K_M) to 7.6 GB (F16).

Phi 3 mini 4k base is a 3.82B-parameter Phi model in GGUF format, quantized by Deeokay. Its trained context length is 4K tokens. The repository has 4 quant files, from 1.9 GB (Q3_K_M) to 7.6 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q3_K_M1.9 GB 4.0 GB
Fits Get file →
Q4_K_M2.3 GB 4.4 GB
Fits Get file →
Q8_04.1 GB 6.2 GB
Fits Get file →
F167.6 GB 9.8 GB
Too big Get file →

What GPU do you need for Phi 3 mini 4k base?

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 Q4_K_M (2.3 GB file, about 6.0 GB in use).
  • 8 GB VRAM: the best quant that fits is Q8_0 (4.1 GB file, about 7.8 GB in use).
  • 12 GB VRAM: the best quant that fits is F16 (7.6 GB file, about 11.4 GB in use).

Which Phi 3 mini 4k base quant should you choose?

Q4_K_M is the usual starting point for Phi 3 mini 4k base: it balances file size and quality well. Here it is a 2.3 GB file.

The Q8_0 file is 4.1 GB, about 1.8 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is Q3_K_M at 1.9 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

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 byDeeokay
FamilyPhi
Licenseapache-2.0
Downloads (HF)60
Last updated2024-07-21

Frequently asked questions about Phi 3 mini 4k base

How much VRAM does Phi 3 mini 4k base need?

About 6.0 GB at Q4_K_M with an 8K context window. That is the 2.3 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 base on an 8 GB GPU?

Yes, with Q8_0: the 4.1 GB file needs about 7.8 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 base GGUF?

It depends on the quant: Q3_K_M is 1.9 GB, Q4_K_M is 2.3 GB, Q8_0 is 4.1 GB, F16 is 7.6 GB.

What context length does Phi 3 mini 4k base 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 base GGUF?

The files are on Hugging Face in the Deeokay/Phi-3-mini-4k-base-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 Phi 3 mini 4k base 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 Deeokay

All by Deeokay →

More Phi models

All Phi →

Other small models

All small models →