JK Ryu · BatiAI

hero775

·

https://flow.bati.ai

rparo20

AI & ML interests

On-device AI, GGUF quantization, Apple Silicon, macOS automation

Recent Activity

updated a collection 14 days ago

🍎 Runs on a 16–32GB Mac — Korean-verified

updated a collection 14 days ago

🆕 Newest Frontier MoE — Korean-verified GGUF

updated a model 14 days ago

batiai/Gravity-30BA5B-RL-GGUF

View all activity

Organizations

updated 2 collections 14 days ago

🍎 Runs on a 16–32GB Mac — Korean-verified

Small enough for an ordinary Mac, and each one actually tested in Korean before release. Chat, OCR, speech and embeddings. • 11 items • Updated 14 days ago

🆕 Newest Frontier MoE — Korean-verified GGUF

Korean output, tool calling and load verified on every tier before publishing. Failures documented on the cards, not omitted. • 8 items • Updated 14 days ago

updated a model 14 days ago

batiai/Gravity-30BA5B-RL-GGUF

Text Generation • 30B • Updated 14 days ago • 659 • 1

published a model 14 days ago

batiai/Gravity-30BA5B-RL-GGUF

Text Generation • 30B • Updated 14 days ago • 659 • 1

updated 3 collections 22 days ago

🍎 Runs on a 16–32GB Mac — Korean-verified

Small enough for an ordinary Mac, and each one actually tested in Korean before release. Chat, OCR, speech and embeddings. • 11 items • Updated 14 days ago

🆕 Newest Frontier MoE — Korean-verified GGUF

Korean output, tool calling and load verified on every tier before publishing. Failures documented on the cards, not omitted. • 8 items • Updated 14 days ago

🍎 Gemma 4 — Google's Latest

Gemma 4 quantizations from Google's official weights. Best entry for 16GB Mac mini M4 (E4B Q4 = 57 t/s). • 5 items • Updated 22 days ago