PH

phi2 hermes2

PhiGGUF by justinj92Updated 2024-02-05
Download on Hugging Face
Parameters2.78B
Context2K
Layers32
Architecturephi2
Smallest quant2.0 GB
Quick answer

phi2 hermes2 needs about 8.7 GB of memory at its main file (a 5.6 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 3 quants, from 2.0 GB (Q5_K_M) to 5.6 GB.

phi2 hermes2 is a 2.78B-parameter Phi model in GGUF format, quantized by justinj92. Its trained context length is 2K tokens. The repository has 3 quant files, from 2.0 GB (Q5_K_M) to 5.6 GB.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q5_K_M2.0 GB 3.2 GB
Fits Get file →
—5.6 GB 6.7 GB
Fits Get file →
—5.6 GB 6.7 GB
Fits Get file →

What GPU do you need for phi2 hermes2?

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: the best quant that fits is Q5_K_M (2.0 GB file, about 5.2 GB in use).
  • 8 GB VRAM: the best quant that fits is Q5_K_M (2.0 GB file, about 5.2 GB in use).
  • 12 GB VRAM: the best quant that fits is the main file (5.6 GB file, about 8.7 GB in use).

Which phi2 hermes2 quant should you choose?

If memory is tight, the smallest file is Q5_K_M at 2.0 GB, with the quality trade-offs that come with fewer bits. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturephi2
Parameters2.78B
Layers32
Trained context2,048 tokens
KV cache (fp16)320 KB per token

Source

Quantized byjustinj92
FamilyPhi
Downloads (HF)31
Last updated2024-02-05

Frequently asked questions about phi2 hermes2

How much VRAM does phi2 hermes2 need?

About 8.7 GB at its main file with an 8K context window. That is the 5.6 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 phi2 hermes2 on an 8 GB GPU?

Yes, with Q5_K_M: the 2.0 GB file needs about 5.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of phi2 hermes2 GGUF?

It depends on the quant: Q5_K_M is 2.0 GB, file is 5.6 GB, file is 5.6 GB.

What context length does phi2 hermes2 support?

The GGUF header lists a trained context length of 2,048 tokens (2K). The KV cache grows with the context you use: about 2.7 GB at 8K and 0.7 GB at 2K.

Where can I download phi2 hermes2 GGUF?

The files are on Hugging Face in the justinj92/phi2-hermes2 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 justinj92

All by justinj92 →

More Phi models

All Phi →

Other tiny models

All tiny models →