PH

Phi 3 Mini 4k Instruct

PhiGGUF by xaskasdfUpdated 2024-08-20
Download on Hugging Face
Parameters3.82B
Context4K
Layers32
Architecturephi3
Smallest quant1.2 GB
Quick answer

Phi 3 Mini 4k Instruct needs about 6.0 GB of memory at IQ4_NL (a 2.3 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 17 quants, from 1.2 GB (IQ2_XXS) to 15.1 GB (F32).

Phi 3 Mini 4k Instruct is a 3.82B-parameter Phi model in GGUF format, quantized by xaskasdf. Its trained context length is 4K tokens. The repository has 17 quant files, from 1.2 GB (IQ2_XXS) to 15.1 GB (F32).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ2_XXS1.2 GB 3.3 GB
Fits Get file →
IQ2_XS1.3 GB 3.4 GB
Fits Get file →
IQ2_S1.3 GB 3.5 GB
Fits Get file →
IQ2_M1.4 GB 3.6 GB
Fits Get file →
Q2_K1.5 GB 3.6 GB
Fits Get file →
Q3_K2.1 GB 4.2 GB
Fits Get file →
IQ4_XS2.2 GB 4.3 GB
Fits Get file →
Q4_02.3 GB 4.4 GB
Fits Get file →
IQ4_NL2.3 GB 4.4 GB
Fits Get file →
Q4_K2.5 GB 4.6 GB
Fits Get file →
Q5_02.8 GB 4.9 GB
Fits Get file →
Q5_K2.9 GB 5.0 GB
Fits Get file →
Q6_K3.3 GB 5.4 GB
Fits Get file →
Q8_04.2 GB 6.3 GB
Fits Get file →
F167.6 GB 9.8 GB
Too big Get file →
BF167.6 GB 9.8 GB
Too big Get file →
F3215.1 GB 17.2 GB
Too big Get file →

What GPU do you need for Phi 3 Mini 4k 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: the best quant that fits is IQ4_NL (2.3 GB file, about 6.0 GB in use).
  • 8 GB VRAM: the best quant that fits is Q8_0 (4.2 GB file, about 7.9 GB in use).
  • 12 GB VRAM: the best quant that fits is BF16 (7.6 GB file, about 11.4 GB in use).
  • 16 GB VRAM: the best quant that fits is BF16 (7.6 GB file, about 11.4 GB in use).
  • 24 GB VRAM: the best quant that fits is F32 (15.1 GB file, about 18.8 GB in use).

Which Phi 3 Mini 4k Instruct quant should you choose?

IQ4_NL (2.3 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.

If memory is tight, the smallest file is IQ2_XXS at 1.2 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturephi3
Parameters3.82B
Layers32
Trained context4,096 tokens
KV cache (fp16)384 KB per token

Source

Quantized byxaskasdf
FamilyPhi
Licensemit
Downloads (HF)163
Last updated2024-08-20

Frequently asked questions about Phi 3 Mini 4k Instruct

How much VRAM does Phi 3 Mini 4k Instruct need?

About 6.0 GB at IQ4_NL 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 Instruct on an 8 GB GPU?

Yes, with Q8_0: the 4.2 GB file needs about 7.9 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 Instruct GGUF?

It depends on the quant: IQ2_XXS is 1.2 GB, IQ2_XS is 1.3 GB, IQ2_S is 1.3 GB, IQ2_M is 1.4 GB, Q2_K is 1.5 GB, Q3_K is 2.1 GB and 11 more.

What context length does Phi 3 Mini 4k Instruct 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 Instruct GGUF?

The files are on Hugging Face in the xaskasdf/phi-3-mini-4k-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 4k 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 xaskasdf

All by xaskasdf →

More Phi models

All Phi →

Other small models

All small models →