README / README.md
hero775's picture
Update README.md
2c431cd verified
metadata
title: BatiAI
emoji: 🍊
colorFrom: indigo
colorTo: purple

BatiAI β€” The Frontier, On Your Mac 🍎

Kimi K2.6 β€” 1T MoE, SWE-Bench Pro 58.6 (beats GPT-5.4 xhigh, Claude Opus 4.6) β€” running locally on M3 Ultra. Gemma 4 E4B β€” 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 β€” direct from official publisher weights, calibrated with imatrix, verified on real hardware, signed with provenance metadata.


⚑ Quick Start

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

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

Pick Your Mac β€” 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 β€” frontier class
Mac Studio M3 Ultra 512GB batiai/kimi-k2.6:iq4 509 GB β€” 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?

πŸ”’ Direct from Source

Quantized from the publisher's official FP8/BF16 weights β€” 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 β€” 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.

πŸš€ Frontier-Capable

We handle 1T MoE (Kimi K2.6) and 229B Dense (MiniMax M2.7). Most providers stop at 70B β€” 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 β€” 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 β€” settlement processing 3 days β†’ 3 hours, 42+ marketplaces. Trusted by COSRX, Pharma Research (Rejuran). Revenue Anomaly Β· Repurchase Cohort Β· Marketing Budget Optimizer.

πŸ“§ jk@bati.ai (enterprise) Β· πŸ’¬ GitHub Issues Β· 🌐 bati.ai


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