PH

Merged

PhiGGUF by yongsen-teoUpdated 2024-08-28
Download on Hugging Face
Parameters—
Context128K
Layers32
Architecturephi3
Smallest quant0.0 GB
Quick answer

Merged needs about 3.7 GB of memory at its main file (a 0.0 GB file) with an 8K context window, so it fits on a 4 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 12.9 GB.

Merged is a Phi model in GGUF format, quantized by yongsen-teo. Its trained context length is 128K tokens. The repository has 1 quant file, from 0.0 GB to 0.0 GB.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 3.7 GB
Fits Get file →

What GPU do you need for Merged?

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: the best quant that fits is the main file (0.0 GB file, about 3.7 GB in use).

Specifications

Architecture from the GGUF header

Architecturephi3
Layers32
Trained context131,072 tokens
KV cache (fp16)384 KB per token

Source

Quantized byyongsen-teo
FamilyPhi
Downloads (HF)4
Last updated2024-08-28

Frequently asked questions about Merged

How much VRAM does Merged need?

About 3.7 GB at its main file with an 8K context window. That is the 0.0 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 Merged on an 8 GB GPU?

Yes, with the smaller files: the 0.0 GB file needs about 3.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Merged GGUF?

It depends on the quant: file is 0.0 GB.

What context length does Merged support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 3.2 GB at 8K and 12.9 GB at 32K.

Where can I download Merged GGUF?

The files are on Hugging Face in the yongsen-teo/merged-phi3.5-v2-checkpoint-1250-27-Aug repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

More from yongsen-teo

All by yongsen-teo →

More Phi models

All Phi →