PH

Phi 3 medium 128k instruct Q8 0

PhiGGUF by ssmitsUpdated 2024-05-21
Download on Hugging Face
Parameters14B
Context128K
Layers40
Architecturephi3
Smallest quant14.8 GB
Quick answer

Phi 3 medium 128k instruct Q8 0 needs about 22.0 GB of memory at Q8_0 (a 14.8 GB file) with an 8K context window, so it fits on a 24 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 26.8 GB.

Phi 3 medium 128k instruct Q8 0 is a 14B-parameter Phi model in GGUF format, quantized by ssmits. Its trained context length is 128K tokens. The repository has 1 quant file, from 14.8 GB (Q8_0) to 14.8 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q8_014.8 GB 22.0 GB
Too big Get file →

What GPU do you need for Phi 3 medium 128k instruct Q8 0?

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 22.0 GB in use).

Which Phi 3 medium 128k instruct Q8 0 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

Architecturephi3
Parameters14B
Layers40
Trained context131,072 tokens
KV cache (fp16)800 KB per token

Source

Quantized byssmits
FamilyPhi
Licensemit
Downloads (HF)13
Last updated2024-05-21

Frequently asked questions about Phi 3 medium 128k instruct Q8 0

How much VRAM does Phi 3 medium 128k instruct Q8 0 need?

About 22.0 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 128k instruct Q8 0 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 22.0 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Phi 3 medium 128k instruct Q8 0 GGUF?

It depends on the quant: Q8_0 is 14.8 GB.

What context length does Phi 3 medium 128k instruct Q8 0 support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 6.7 GB at 8K and 26.8 GB at 32K.

Where can I download Phi 3 medium 128k instruct Q8 0 GGUF?

The files are on Hugging Face in the ssmits/Phi-3-medium-128k-instruct-Q8_0-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 Phi 3 medium 128k instruct Q8 0 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 ssmits

All by ssmits →

More Phi models

All Phi →

Other medium models

All medium models →