This repo contains the llama.cpp compatible GGUFs of vikhyatk/moondream2: https://huggingface.co/vikhyatk/moondream2.

The GGUFs hosted in the original repo is missing the tokenizer.chat_template field, thanks to @Hahasb for adding the vicuna template.

For further discussion, please refer to the PR: https://github.com/ggml-org/llama.cpp/pull/13745

Downloads last month
980
GGUF
Model size
454M params
Architecture
clip
Hardware compatibility
Log In to view the estimation

16-bit

Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for ggml-org/moondream2-20250414-GGUF

Quantized
(3)
this model

Collection including ggml-org/moondream2-20250414-GGUF