PH

patched phi 3.5

PhiGGUF by patched-codesUpdated 2024-08-21
Download on Hugging Face
Parameters3.82B
Context128K
Layers32
Architecturellama
Smallest quant2.3 GB
Quick answer

patched phi 3.5 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 (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 12.9 GB.

patched phi 3.5 is a 3.82B-parameter Phi model in GGUF format, quantized by patched-codes. Its trained context length is 128K tokens. The repository has 2 quant files, from 2.3 GB (Q4_K_M) to 7.6 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M2.3 GB 6.0 GB
Fits Get file →
F167.6 GB 11.4 GB
Too big Get file →

What GPU do you need for patched phi 3.5?

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 F16 (7.6 GB file, about 11.4 GB in use).

Which patched phi 3.5 quant should you choose?

Q4_K_M is the usual starting point for patched phi 3.5: 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 context131,072 tokens
KV cache (fp16)384 KB per token

Source

Quantized bypatched-codes
FamilyPhi
Licenseapache-2.0
Downloads (HF)40
Last updated2024-08-21

Frequently asked questions about patched phi 3.5

How much VRAM does patched phi 3.5 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 patched phi 3.5 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 patched phi 3.5 GGUF?

It depends on the quant: Q4_K_M is 2.3 GB, F16 is 7.6 GB.

What context length does patched phi 3.5 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 patched phi 3.5 GGUF?

The files are on Hugging Face in the patched-codes/patched-phi-3.5-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 patched phi 3.5 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 patched-codes

All by patched-codes →

More Phi models

All Phi →

Other small models

All small models →