PH

phi 3 4k

PhiGGUF by empgcesUpdated 2024-08-30
Download on Hugging Face
Parameters1.1B
Context4K
Layers22
Architecturellama
Smallest quant0.7 GB
Quick answer

phi 3 4k needs about 1.4 GB of memory at Q4_K_M (a 0.7 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 3 quants, from 0.7 GB (Q4_K_M) to 2.2 GB (F16).

phi 3 4k is a 1.1B-parameter Phi model in GGUF format, quantized by empgces. Its trained context length is 4K tokens. The repository has 3 quant files, from 0.7 GB (Q4_K_M) to 2.2 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M0.7 GB 1.3 GB
Fits Get file →
Q8_01.2 GB 1.8 GB
Fits Get file →
F162.2 GB 2.8 GB
Fits Get file →

What GPU do you need for phi 3 4k?

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: the best quant that fits is F16 (2.2 GB file, about 2.9 GB in use).

Which phi 3 4k quant should you choose?

Q4_K_M is the usual starting point for phi 3 4k: it balances file size and quality well. Here it is a 0.7 GB file.

The Q8_0 file is 1.2 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.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters1.1B
Layers22
Trained context4,096 tokens
KV cache (fp16)22 KB per token

Source

Quantized byempgces
FamilyPhi
Downloads (HF)6
Last updated2024-08-30

Frequently asked questions about phi 3 4k

How much VRAM does phi 3 4k need?

About 1.4 GB at Q4_K_M with an 8K context window. That is the 0.7 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 4k on an 8 GB GPU?

Yes, with F16: the 2.2 GB file needs about 2.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

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

It depends on the quant: Q4_K_M is 0.7 GB, Q8_0 is 1.2 GB, F16 is 2.2 GB.

What context length does phi 3 4k support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 0.2 GB at 8K and 0.1 GB at 4K.

Where can I download phi 3 4k GGUF?

The files are on Hugging Face in the empgces/phi_3_4k_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 empgces

All by empgces →

More Phi models

All Phi →

Other tiny models

All tiny models →