PH

phi4 MedIT 10B o1

PhiGGUF by mkurmanUpdated 2025-01-18
Download on Hugging Face
Parameters10.3B
Context16K
Layers40
Architecturellama
Smallest quant10.9 GB
Quick answer

phi4 MedIT 10B o1 needs about 13.1 GB of memory at its main file (a 10.9 GB file) with an 8K context window, so it fits on a 16 GB GPU.

phi4 MedIT 10B o1 is a 10.3B-parameter Phi model in GGUF format, quantized by mkurman. Its trained context length is 16K tokens. The repository has 1 quant file, from 10.9 GB to 10.9 GB.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—10.9 GB 13.1 GB
Too big Get file →

What GPU do you need for phi4 MedIT 10B o1?

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: no quant fits at an 8K context.
  • 16 GB VRAM: the best quant that fits is the main file (10.9 GB file, about 13.1 GB in use).

Specifications

Architecture from the GGUF header

Architecturellama
Parameters10.3B
Layers40
Trained context16,384 tokens
KV cache (fp16)200 KB per token

Source

Quantized bymkurman
FamilyPhi
Licensemit
Downloads (HF)452
Last updated2025-01-18

Frequently asked questions about phi4 MedIT 10B o1

How much VRAM does phi4 MedIT 10B o1 need?

About 13.1 GB at its main file with an 8K context window. That is the 10.9 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 MedIT 10B o1 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 13.1 GB, so you would need a larger GPU or CPU offloading.

What is the file size of phi4 MedIT 10B o1 GGUF?

It depends on the quant: file is 10.9 GB.

What context length does phi4 MedIT 10B o1 support?

The GGUF header lists a trained context length of 16,384 tokens (16K). The KV cache grows with the context you use: about 1.7 GB at 8K and 3.4 GB at 16K.

Where can I download phi4 MedIT 10B o1 GGUF?

The files are on Hugging Face in the mkurman/phi4-MedIT-10B-o1 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 MedIT 10B o1 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 mkurman

All by mkurman →

More Phi models

All Phi →

Other medium models

All medium models →