PH

Phi 3 mini 128k instruct

PhiGGUF by ZeroWwUpdated 2024-07-03
Download on Hugging Face
Parameters3.82B
Context128K
Layers32
Architecturephi3
Smallest quant3.1 GB
Quick answer

Phi 3 mini 128k instruct needs about 7.1 GB of memory at Q6_K (a 3.4 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 4 quants, from 3.1 GB (Q5_K) to 7.6 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 12.9 GB.

Phi 3 mini 128k instruct is a 3.82B-parameter Phi model in GGUF format, quantized by ZeroWw. Its trained context length is 128K tokens. The repository has 4 quant files, from 3.1 GB (Q5_K) to 7.6 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q5_K3.1 GB 6.8 GB
Fits Get file →
Q6_K3.4 GB 7.1 GB
Fits Get file →
Q8_04.2 GB 8.0 GB
Tight Get file →
F167.6 GB 11.4 GB
Too big Get file →

What GPU do you need for Phi 3 mini 128k instruct?

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 Q8_0 (4.2 GB file, about 8.0 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 128k instruct quant should you choose?

Q6_K (3.4 GB) is the middle option in this repository. Very close to the original quality for most uses, at a clearly larger size than 4-bit.

If memory is tight, the smallest file is Q5_K at 3.1 GB, with the quality trade-offs that come with fewer bits. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturephi3
Parameters3.82B
Layers32
Trained context131,072 tokens
KV cache (fp16)384 KB per token

Source

Quantized byZeroWw
FamilyPhi
Licensemit
Downloads (HF)50
Last updated2024-07-03

Frequently asked questions about Phi 3 mini 128k instruct

How much VRAM does Phi 3 mini 128k instruct need?

About 7.1 GB at Q6_K with an 8K context window. That is the 3.4 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 128k instruct on an 8 GB GPU?

Yes, with Q8_0: the 4.2 GB file needs about 8.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Phi 3 mini 128k instruct GGUF?

It depends on the quant: Q5_K is 3.1 GB, Q6_K is 3.4 GB, Q8_0 is 4.2 GB, F16 is 7.6 GB.

What context length does Phi 3 mini 128k instruct support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 3.2 GB at 8K and 12.9 GB at 32K.

Where can I download Phi 3 mini 128k instruct GGUF?

The files are on Hugging Face in the ZeroWw/Phi-3-mini-128k-instruct-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 128k instruct use?

Hugging Face lists the license as mit. 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 ZeroWw

All by ZeroWw →

More Phi models

All Phi →

Other small models

All small models →