PH

unsloth_phi3-8bit

PhiGGUF by anil1002Updated 2024-05-30
Download on Hugging Face
Parameters3.82B
Context4K
Layers32
Architecturellama
Smallest quant4.1 GB
Quick answer

unsloth_phi3-8bit needs about 7.8 GB of memory at Q8_0 (a 4.1 GB file) with an 8K context window, so it fits on a 8 GB GPU.

unsloth_phi3-8bit is a 3.82B-parameter Phi model in GGUF format, quantized by anil1002. Its trained context length is 4K tokens. The repository has 1 quant file, from 4.1 GB (Q8_0) to 4.1 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q8_04.1 GB 6.2 GB
Fits Get file →

What GPU do you need for unsloth_phi3-8bit?

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: the best quant that fits is Q8_0 (4.1 GB file, about 7.8 GB in use).

Which unsloth_phi3-8bit quant should you choose?

Q8_0 (4.1 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
Parameters3.82B
Layers32
Trained context4,096 tokens
KV cache (fp16)384 KB per token

Source

Quantized byanil1002
FamilyPhi
Downloads (HF)14
Last updated2024-05-30

Frequently asked questions about unsloth_phi3-8bit

How much VRAM does unsloth_phi3-8bit need?

About 7.8 GB at Q8_0 with an 8K context window. That is the 4.1 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 unsloth_phi3-8bit on an 8 GB GPU?

Yes, with Q8_0: the 4.1 GB file needs about 7.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of unsloth_phi3-8bit GGUF?

It depends on the quant: Q8_0 is 4.1 GB.

What context length does unsloth_phi3-8bit support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 3.2 GB at 8K and 1.6 GB at 4K.

Where can I download unsloth_phi3-8bit GGUF?

The files are on Hugging Face in the anil1002/unsloth_phi3-8bit_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 anil1002

All by anil1002 →

More Phi models

All Phi →

Other small models

All small models →