Clef

Run it in the Llama app: https://llama.app

Or from the terminal:

llama serve -hf ggml-org/Clef-GGUF

This is a decision model, to be used via /v1/systemone API. Requires https://github.com/ggml-org/llama.cpp/pull/29831

> [!IMPORTANT]

> This model is automatically converted using https://github.com/ggml-org/convert

Question 2

What license applies to ggml-org/Clef-GGUF?

Accepted Answer

License: apache-2.0. Verify terms on Hugging Face before commercial use.

Question 3

How do I run ggml-org/Clef-GGUF locally?

Accepted Answer

Download a GGUF file from this page and load it in guIDE or llama.cpp. Pipeline task: image-text-to-text.

Question 4

How much VRAM or disk space does ggml-org/Clef-GGUF need?

Accepted Answer

Runs locally from ~600.1 MB disk (4 GB VRAM class GPUs with llama.cpp / guIDE).

File	Type	Quantization	Size	Link
Clef-BF16.gguf	GGUF	BF16	50.35 GB	Download
Clef-Q4_K_M.gguf	GGUF	Q4_K_M	17.91 GB	Download
Clef-Q8_0.gguf	GGUF	Q8_0	26.76 GB	Download
mmproj-Clef-BF16.gguf	GGUF	BF16	888.0 MB	Download
mmproj-Clef-Q8_0.gguf	GGUF	Q8_0	600.1 MB	Download

ggml-org/Clef-GGUF overview