PH

Phi 3 medium 4k med

PhiGGUF by eason522Updated 2024-07-20
Download on Hugging Face
Parameters3.82B
Context4K
Layers32
Architecturellama
Smallest quant2.3 GB
Quick answer

Phi 3 medium 4k med 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 2 quants, from 2.3 GB (Q4_K_M) to 7.6 GB (BF16).

Phi 3 medium 4k med is a 3.82B-parameter Phi model in GGUF format, quantized by eason522. Its trained context length is 4K tokens. The repository has 2 quant files, from 2.3 GB (Q4_K_M) to 7.6 GB (BF16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M2.3 GB 4.4 GB
Fits Get file →
BF167.6 GB 9.8 GB
Too big Get file →

What GPU do you need for Phi 3 medium 4k med?

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 Q4_K_M (2.3 GB file, about 6.0 GB in use).
  • 12 GB VRAM: the best quant that fits is BF16 (7.6 GB file, about 11.4 GB in use).

Which Phi 3 medium 4k med quant should you choose?

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

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 byeason522
FamilyPhi
Licenseapache-2.0
Downloads (HF)9
Last updated2024-07-20

Frequently asked questions about Phi 3 medium 4k med

How much VRAM does Phi 3 medium 4k med 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 medium 4k med on an 8 GB GPU?

Yes, with Q4_K_M: the 2.3 GB file needs about 6.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Phi 3 medium 4k med GGUF?

It depends on the quant: Q4_K_M is 2.3 GB, BF16 is 7.6 GB.

What context length does Phi 3 medium 4k med 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 medium 4k med GGUF?

The files are on Hugging Face in the eason522/Phi-3-medium-4k-med 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 medium 4k med 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 eason522

All by eason522 →

More Phi models

All Phi →

Other small models

All small models →