PH

Shiny Phi3.5

PhiGGUF by johnsoupirUpdated 2024-09-10
Download on Hugging Face
Parameters3.82B
Context4K
Layers32
Architecturellama
Smallest quant2.3 GB
Quick answer

Shiny Phi3.5 needs about 6.0 GB of memory at Q4_K_M (a 2.3 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 3 quants, from 2.3 GB (Q4_K_M) to 7.6 GB (F16).

Shiny Phi3.5 is a 3.82B-parameter Phi model in GGUF format, quantized by johnsoupir. Its trained context length is 4K tokens. The repository has 3 quant files, from 2.3 GB (Q4_K_M) to 7.6 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M2.3 GB 4.4 GB
Fits Get file →
—4.1 GB 6.2 GB
Fits Get file →
F167.6 GB 9.8 GB
Too big Get file →

What GPU do you need for Shiny Phi3.5?

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 Q4_K_M (2.3 GB file, about 6.0 GB in use).
  • 8 GB VRAM: the best quant that fits is the main file (4.1 GB file, about 7.8 GB in use).
  • 12 GB VRAM: the best quant that fits is F16 (7.6 GB file, about 11.4 GB in use).

Which Shiny Phi3.5 quant should you choose?

Q4_K_M is the usual starting point for Shiny Phi3.5: it balances file size and quality well. Here it is a 2.3 GB file.

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 byjohnsoupir
FamilyPhi
Downloads (HF)43
Last updated2024-09-10

Frequently asked questions about Shiny Phi3.5

How much VRAM does Shiny Phi3.5 need?

About 6.0 GB at Q4_K_M with an 8K context window. That is the 2.3 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 Shiny Phi3.5 on an 8 GB GPU?

Yes, with the smaller files: 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 Shiny Phi3.5 GGUF?

It depends on the quant: Q4_K_M is 2.3 GB, file is 4.1 GB, F16 is 7.6 GB.

What context length does Shiny Phi3.5 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 Shiny Phi3.5 GGUF?

The files are on Hugging Face in the johnsoupir/Shiny-Phi3.5 repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Other GGUFs of Phi-3.5-mini-instruct

Similar models

Browse all →

More Phi models

All Phi →

Other small models

All small models →