PH

Phi 3 medium 4k instruct 4bit nuclear chat

PhiGGUF by inetnucUpdated 2024-07-28
Download on Hugging Face
Parameters14B
Context4K
Layers40
Architecturellama
Smallest quant14.8 GB
Quick answer

Phi 3 medium 4k instruct 4bit nuclear chat needs about 17.0 GB of memory at Q8_0 (a 14.8 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 2 quants, from 14.8 GB (Q8_0) to 27.9 GB (F16).

Phi 3 medium 4k instruct 4bit nuclear chat is a 14B-parameter Phi model in GGUF format, quantized by inetnuc. Its trained context length is 4K tokens. The repository has 2 quant files, from 14.8 GB (Q8_0) to 27.9 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q8_014.8 GB 16.2 GB
Too big Get file →
F1627.9 GB 29.3 GB
Too big Get file →

What GPU do you need for Phi 3 medium 4k instruct 4bit nuclear chat?

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: no quant fits at an 8K context.
  • 24 GB VRAM: the best quant that fits is Q8_0 (14.8 GB file, about 17.0 GB in use).
  • 32 GB VRAM: the best quant that fits is F16 (27.9 GB file, about 30.1 GB in use).

Which Phi 3 medium 4k instruct 4bit nuclear chat quant should you choose?

Q8_0 (14.8 GB) is the middle option in this repository. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters14B
Layers40
Trained context4,096 tokens
KV cache (fp16)200 KB per token

Source

Quantized byinetnuc
FamilyPhi
Licenseapache-2.0
Downloads (HF)44
Last updated2024-07-28

Frequently asked questions about Phi 3 medium 4k instruct 4bit nuclear chat

How much VRAM does Phi 3 medium 4k instruct 4bit nuclear chat need?

About 17.0 GB at Q8_0 with an 8K context window. That is the 14.8 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 medium 4k instruct 4bit nuclear chat on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 17.0 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Phi 3 medium 4k instruct 4bit nuclear chat GGUF?

It depends on the quant: Q8_0 is 14.8 GB, F16 is 27.9 GB.

What context length does Phi 3 medium 4k instruct 4bit nuclear chat support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 1.7 GB at 8K and 0.8 GB at 4K.

Where can I download Phi 3 medium 4k instruct 4bit nuclear chat GGUF?

The files are on Hugging Face in the inetnuc/Phi-3-medium-4k-instruct-4bit-nuclear-chat repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Phi 3 medium 4k instruct 4bit nuclear chat 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 inetnuc

All by inetnuc →

More Phi models

All Phi →

Other medium models

All medium models →