PH

bling phi 3 RAG chunked

PhiGGUF by BoscoTheDogUpdated 2024-05-31
Download on Hugging Face
Parameters3.82B
Context4K
Layers32
Architecturephi3
Smallest quant2.4 GB
Quick answer

bling phi 3 RAG chunked needs about 6.1 GB of memory at its main file (a 2.4 GB file) with an 8K context window, so it fits on a 8 GB GPU.

bling phi 3 RAG chunked is a 3.82B-parameter Phi model in GGUF format, quantized by BoscoTheDog. Its trained context length is 4K tokens. The repository has 1 quant file, from 2.4 GB to 2.4 GB.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—2.4 GB (12 parts) 4.5 GB
Fits Get file →

What GPU do you need for bling phi 3 RAG chunked?

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 the main file (2.4 GB file, about 6.1 GB in use).

Specifications

Architecture from the GGUF header

Architecturephi3
Parameters3.82B
Layers32
Trained context4,096 tokens
KV cache (fp16)384 KB per token

Source

Quantized byBoscoTheDog
FamilyPhi
Downloads (HF)4
Last updated2024-05-31

Frequently asked questions about bling phi 3 RAG chunked

How much VRAM does bling phi 3 RAG chunked need?

About 6.1 GB at its main file with an 8K context window. That is the 2.4 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 bling phi 3 RAG chunked on an 8 GB GPU?

Yes, with the smaller files: the 2.4 GB file needs about 6.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of bling phi 3 RAG chunked GGUF?

It depends on the quant: file is 2.4 GB.

What context length does bling phi 3 RAG chunked 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 bling phi 3 RAG chunked GGUF?

The files are on Hugging Face in the BoscoTheDog/bling_phi_3_RAG_chunked 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 BoscoTheDog

All by BoscoTheDog →

More Phi models

All Phi →

Other small models

All small models →