PH

phi4_SFT_WSD_merged

PhiGGUF by turkeyboy2012Updated 2025-11-11
Download on Hugging Face
Parameters3.84B
Context128K
Layers32
Architecturephi3
Smallest quant7.7 GB
Quick answer

phi4_SFT_WSD_merged needs about 9.3 GB of memory at its main file (a 7.7 GB file) with an 8K context window, so it fits on a 12 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

phi4_SFT_WSD_merged is a 3.84B-parameter Phi model in GGUF format, quantized by turkeyboy2012. Its trained context length is 128K tokens. The repository has 1 quant file, from 7.7 GB to 7.7 GB.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—7.7 GB 9.3 GB
Too big Get file →

What GPU do you need for phi4_SFT_WSD_merged?

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: no quant fits at an 8K context.
  • 12 GB VRAM: the best quant that fits is the main file (7.7 GB file, about 9.3 GB in use).

Specifications

Architecture from the GGUF header

Architecturephi3
Parameters3.84B
Layers32
Trained context131,072 tokens
KV cache (fp16)128 KB per token

Source

Quantized byturkeyboy2012
FamilyPhi
Licensecc-by-4.0
Downloads (HF)2
Last updated2025-11-11

Frequently asked questions about phi4_SFT_WSD_merged

How much VRAM does phi4_SFT_WSD_merged need?

About 9.3 GB at its main file with an 8K context window. That is the 7.7 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 phi4_SFT_WSD_merged on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 9.3 GB, so you would need a larger GPU or CPU offloading.

What is the file size of phi4_SFT_WSD_merged GGUF?

It depends on the quant: file is 7.7 GB.

What context length does phi4_SFT_WSD_merged support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.

Where can I download phi4_SFT_WSD_merged GGUF?

The files are on Hugging Face in the turkeyboy2012/phi4_SFT_WSD repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does phi4_SFT_WSD_merged use?

Hugging Face lists the license as cc-by-4.0. 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 turkeyboy2012

All by turkeyboy2012 →

More Phi models

All Phi →

Other small models

All small models →