PH

phi-pycode

PhiGGUF by MohamedSaeed-devUpdated 2024-06-03
Download on Hugging Face
Parameters3.82B
Context4K
Layers32
Architecturellama
Smallest quant7.6 GB
Quick answer

phi-pycode needs about 11.4 GB of memory at F16 (a 7.6 GB file) with an 8K context window, so it fits on a 12 GB GPU.

phi-pycode is a 3.82B-parameter Phi model in GGUF format, quantized by MohamedSaeed-dev. Its trained context length is 4K tokens. The repository has 1 quant file, from 7.6 GB (F16) to 7.6 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
F167.6 GB 9.8 GB
Too big Get file →

What GPU do you need for phi-pycode?

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

Which phi-pycode quant should you choose?

F16 (7.6 GB) is the middle option in this repository. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.

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 byMohamedSaeed-dev
FamilyPhi
Downloads (HF)7
Last updated2024-06-03

Frequently asked questions about phi-pycode

How much VRAM does phi-pycode need?

About 11.4 GB at F16 with an 8K context window. That is the 7.6 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-pycode on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 11.4 GB, so you would need a larger GPU or CPU offloading.

What is the file size of phi-pycode GGUF?

It depends on the quant: F16 is 7.6 GB.

What context length does phi-pycode 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-pycode GGUF?

The files are on Hugging Face in the MohamedSaeed-dev/phi-pycode-f16-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 MohamedSaeed-dev

All by MohamedSaeed-dev →

More Phi models

All Phi →

Other small models

All small models →