BatiAI

company

https://flow.bati.ai/

AI & ML interests

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

Recent Activity

hero775 updated a model 1 day ago

batiai/DeepSeek-V4-Pro-GGUF

hero775 updated a collection 3 days ago

🚀 Frontier MoE — 128B–1T

hero775 updated a model 3 days ago

batiai/Llama-4-Scout-17B-16E-Instruct-GGUF

View all activity

updated a model 1 day ago

batiai/DeepSeek-V4-Pro-GGUF

Text Generation • 1.6T • Updated about 11 hours ago • 1.26k • 1

updated a collection 3 days ago

🚀 Frontier MoE — 128B–1T

Largest open-weight LLMs, BatiAI-quantized. Mac-runnable from M4 Max 128GB to Mac Studio M3 Ultra 512GB. • 7 items • Updated 3 days ago

updated a model 3 days ago

batiai/Llama-4-Scout-17B-16E-Instruct-GGUF

Image-Text-to-Text • 108B • Updated 3 days ago • 2.38k

published a model 3 days ago

batiai/Llama-4-Scout-17B-16E-Instruct-GGUF

Image-Text-to-Text • 108B • Updated 3 days ago • 2.38k

updated a collection 5 days ago

🚀 Frontier MoE — 128B–1T

Largest open-weight LLMs, BatiAI-quantized. Mac-runnable from M4 Max 128GB to Mac Studio M3 Ultra 512GB. • 7 items • Updated 3 days ago

published a model 6 days ago

batiai/DeepSeek-V4-Pro-GGUF

Text Generation • 1.6T • Updated about 11 hours ago • 1.26k • 1

updated a model 11 days ago

batiai/Nemotron-3-Nano-Omni-30B-Text-Only-GGUF

Text Generation • 32B • Updated 11 days ago • 2.03k

updated a collection 13 days ago

🚀 Frontier MoE — 128B–1T

Largest open-weight LLMs, BatiAI-quantized. Mac-runnable from M4 Max 128GB to Mac Studio M3 Ultra 512GB. • 7 items • Updated 3 days ago

updated a model 14 days ago

batiai/GLM-5.1-GGUF

Text Generation • 754B • Updated 13 days ago • 1.43k

published a model 14 days ago

batiai/GLM-5.1-GGUF

Text Generation • 754B • Updated 13 days ago • 1.43k

updated 2 collections 16 days ago

🧠 NVIDIA Nemotron 3 — Hybrid Mamba+Attention

NVIDIA Nemotron 3 family — NemotronH architecture combining Mamba state-space + standard attention. Mac-runnable, BatiAI-quantized + signed. • 3 items • Updated 16 days ago

🚀 Frontier MoE — 128B–1T

Largest open-weight LLMs, BatiAI-quantized. Mac-runnable from M4 Max 128GB to Mac Studio M3 Ultra 512GB. • 7 items • Updated 3 days ago

updated 2 models 16 days ago

batiai/Mistral-Medium-3.5-128B-GGUF

Text Generation • 125B • Updated 16 days ago • 770

batiai/Nemotron-3-Nano-30B-A3B-GGUF

Text Generation • 32B • Updated 16 days ago • 1.53k

updated a collection 16 days ago

🚀 Frontier MoE — 128B–1T

Largest open-weight LLMs, BatiAI-quantized. Mac-runnable from M4 Max 128GB to Mac Studio M3 Ultra 512GB. • 7 items • Updated 3 days ago

updated 2 models 17 days ago

batiai/Granite-4.1-8B-GGUF

Text Generation • 9B • Updated 16 days ago • 627

batiai/Qwen3.5-35B-A3B-GGUF

Text Generation • 35B • Updated 17 days ago • 490