README.md

metadata

title: BatiAI
emoji: 🍊
colorFrom: indigo
colorTo: purple

BatiAI — The Frontier, On Your Mac 🍎

Kimi K2.6 — 1T MoE, SWE-Bench Pro 58.6 (beats GPT-5.4 xhigh, Claude Opus 4.6) — running locally on M3 Ultra. Gemma 4 E4B — 57 tokens/sec on a 16GB Mac mini M4. No API costs. No rate limits. No cloud.

We quantize popular open-weight models for every Mac — direct from official publisher weights, calibrated with imatrix, verified on real hardware, signed with provenance metadata.

---

⚡ Quick Start

# 16GB Mac mini M4 — entry, 57 t/s
ollama pull batiai/gemma4-e4b:q4

# 512GB M3 Ultra — 1T MoE frontier
ollama pull batiai/kimi-k2.6:iq4

---

Pick Your Mac — Real Hardware Benchmarks

Every speed measured on actual hardware. Full reports in each model card. We continuously add new hardware as it ships.

Your Mac	Best Pick	Size	Speed	Use Case
Mac mini M4 16GB	batiai/gemma4-e4b:q4	5.0 GB	57 t/s	Daily chat, balanced
MacBook Air 16GB	batiai/qwen3.5-9b:q4	5.2 GB	12.5 t/s	Tool calling, JSON
Mac mini M4 Pro 24GB	batiai/gemma4-26b:iq4	15 GB	85 t/s	MoE, larger context
MacBook Pro 48GB	batiai/qwen3.6-35b:iq4	22 GB	~30 t/s	Tools + thinking, MoE
MacBook Pro 96GB	batiai/qwen3.6-35b:q6	29 GB	~27 t/s	Top quality chat
MacBook Pro M4 Max 128GB	batiai/minimax-m2.7:iq3	82 GB	36.7 t/s	229B Dense — frontier class
Mac Studio M3 Ultra 512GB	batiai/kimi-k2.6:iq4	509 GB	—	1T MoE, SWE-Bench Pro 58.6

Real measurements, not estimates. Numbers expand as benchmarks come in.

Browse the Collections below ↓ for series-by-series lineup.

---

🎯 Why BatiAI?

🔒 Direct from Source Quantized from the publisher's official FP8/BF16 weights — never re-quantized from third-party GGUFs. Every file signed general.author=BatiAI + general.url=https://flow.bati.ai so you always know where it came from.	🍎 Verified on Real Macs Tested on Mac mini M4 16GB + MacBook Pro M4 Max 128GB. Korean validation, tool-call JSON, 200-token throughput — measured, reproducible, documented in each model card.
⚡ imatrix-Calibrated Every model uses importance-matrix calibration with wikitext-2. Aggressive IQ3_XXS keeps quality where plain Q3_K_M visibly degrades.	🚀 Frontier-Capable We handle 1T MoE (Kimi K2.6) and 229B Dense (MiniMax M2.7). Most providers stop at 70B — we have the storage, pipeline, and experience to go further.

---

🧰 Built for Real Mac Users

BatiFlow	5MB native macOS app. Connects BatiAI models to 60+ tools — KakaoTalk, iMessage, Slack, Calendar, Notes, Chrome, file system, browser. Free. Unlimited. 100% private. Even drives your Mac via Telegram / Discord / Slack bots.
Bati CIS	K-Beauty Commerce Intelligence — settlement processing 3 days → 3 hours, 42+ marketplaces. Trusted by COSRX, Pharma Research (Rejuran). Revenue Anomaly · Repurchase Cohort · Marketing Budget Optimizer.

---

📧 jk@bati.ai (enterprise) · 💬 GitHub Issues · 🌐 bati.ai

---

Private by default · On-device first · Verified every step.