PH

PhoGPT-7B5

PhogptGGUF by hoangtonUpdated 2023-12-16
Download on Hugging Face
Parameters8.5B
Context2K
Layers32
Architecturempt
Smallest quant17.0 GB
Quick answer

PhoGPT-7B5 needs about 21.8 GB of memory at its main file (a 17.0 GB file) with an 8K context window, so it fits on a 24 GB GPU.

PhoGPT-7B5 is a 8.5B-parameter Phogpt model in GGUF format, quantized by hoangton. Its trained context length is 2K tokens. The repository has 1 quant file, from 17.0 GB to 17.0 GB.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—17.0 GB 18.6 GB
Too big Get file →

What GPU do you need for PhoGPT-7B5?

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 the main file (17.0 GB file, about 21.8 GB in use).

Specifications

Architecture from the GGUF header

Architecturempt
Parameters8.5B
Layers32
Trained context2,048 tokens
KV cache (fp16)512 KB per token

Source

Quantized byhoangton
FamilyPhogpt
Downloads (HF)51
Last updated2023-12-16

Frequently asked questions about PhoGPT-7B5

How much VRAM does PhoGPT-7B5 need?

About 21.8 GB at its main file with an 8K context window. That is the 17.0 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 PhoGPT-7B5 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 21.8 GB, so you would need a larger GPU or CPU offloading.

What is the file size of PhoGPT-7B5 GGUF?

It depends on the quant: file is 17.0 GB.

What context length does PhoGPT-7B5 support?

The GGUF header lists a trained context length of 2,048 tokens (2K). The KV cache grows with the context you use: about 4.3 GB at 8K and 1.1 GB at 2K.

Where can I download PhoGPT-7B5 GGUF?

The files are on Hugging Face in the hoangton/PhoGPT-7B5-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 hoangton

All by hoangton →

More Phogpt models

All Phogpt →

Other small models

All small models →