PH

tofuTune-phi3-medium-gguf

PhiGGUF by simonbuttUpdated 2024-05-24
Download on Hugging Face
Parameters14B
Context4K
Layers40
Architecturellama
Smallest quant8.4 GB
Quick answer

tofuTune-phi3-medium-gguf needs about 10.6 GB of memory at Q4_K_M (a 8.4 GB file) with an 8K context window, so it fits on a 12 GB GPU.

tofuTune-phi3-medium-gguf is a 14B-parameter Phi model in GGUF format, quantized by simonbutt. Its trained context length is 4K tokens. The repository has 1 quant file, from 8.4 GB (Q4_K_M) to 8.4 GB (Q4_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M8.4 GB 9.7 GB
Too big Get file →

What GPU do you need for tofuTune-phi3-medium-gguf?

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: no quant fits at an 8K context.
  • 12 GB VRAM: the best quant that fits is Q4_K_M (8.4 GB file, about 10.6 GB in use).

Which tofuTune-phi3-medium-gguf quant should you choose?

Q4_K_M is the usual starting point for tofuTune-phi3-medium-gguf: it balances file size and quality well. Here it is a 8.4 GB file.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters14B
Layers40
Trained context4,096 tokens
KV cache (fp16)200 KB per token

Source

Quantized bysimonbutt
FamilyPhi
Licenseapache-2.0
Downloads (HF)8
Last updated2024-05-24

Frequently asked questions about tofuTune-phi3-medium-gguf

How much VRAM does tofuTune-phi3-medium-gguf need?

About 10.6 GB at Q4_K_M with an 8K context window. That is the 8.4 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 tofuTune-phi3-medium-gguf on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 10.6 GB, so you would need a larger GPU or CPU offloading.

What is the file size of tofuTune-phi3-medium-gguf GGUF?

It depends on the quant: Q4_K_M is 8.4 GB.

What context length does tofuTune-phi3-medium-gguf support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 1.7 GB at 8K and 0.8 GB at 4K.

Where can I download tofuTune-phi3-medium-gguf GGUF?

The files are on Hugging Face in the simonbutt/tofuTune-phi3-medium-gguf repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does tofuTune-phi3-medium-gguf use?

Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Other GGUFs of Phi-3-medium-4k-instruct-bnb-4bit

Similar models

Browse all →

More from simonbutt

All by simonbutt →

More Phi models

All Phi →

Other medium models

All medium models →