kabirlabs/diaryai-gguf-models

DiaryAI GGUF Models

Quantized GGUF models used for on-device inference in the DiaryAI mobile app (via llama.rn / llama.cpp). These are re-hosted copies of publicly released models, uploaded here to guarantee a stable, unchanging download URL for the app.

Models

File	Source	Size	License
qwen2.5-0.5b-instruct-q4_k_m.gguf	Qwen/Qwen2.5-0.5B-Instruct-GGUF	469 MB	Apache 2.0
gemma-3-1b-it-q4_k_m.gguf	DravenBlack/gemma-3-1b-it-Q4_K_M-GGUF, originally google/gemma-3-1b-it	769 MB	Gemma Terms of Use
Qwen3-4B-Instruct-2507-UD-Q4_K_XL.gguf	unsloth/Qwen3-4B-Instruct-2507-GGUF	2.4 GB	Apache 2.0

Notes

• Files are unmodified byte-for-byte from their source repos above — only re-hosted.
• The Gemma model is distributed under Google's Gemma Terms of Use. By downloading gemma-3-1b-it-q4_k_m.gguf you agree to those terms. See NOTICE.md.
• The Qwen models are Apache 2.0 licensed and redistributed as permitted by that license.