Mac-1 — 6.6B Local AI Agent for macOS
Source: Threads post by @aditya.rao310 / X/Twitter by @cjzafir
What It Is
Mac-1 is a 6.6B parameter model (fine-tuned on Qwen 3.5 series) that runs entirely offline on any Mac. Built by @cjzafir with a full native macOS application layer.
Key Specs
| Spec | Value |
|---|---|
| Model size | 6.6B parameters (4B + 2B dense) |
| RAM required | 7GB (12GB ideal) |
| Speed | ~65 tok/s with reasoning ON |
| macOS tools | 487 native tools |
| Quantization | Q4_K_M — 99% accuracy |
| Training data | 670M handcrafted tokens, 113K+ rows |
| Connectivity | Works fully offline |
What It Can Do
Chains together native macOS tools to accomplish multi-step tasks from a single instruction:
- Schedule a meeting
- Set a reminder
- Draft a follow-up email
- All in one instruction, no internet needed
Why It Matters
- Truly native macOS app, not a web wrapper
- Offline-first — no cloud dependency
- Tool chaining — 487 tools composed into multi-step workflows
- Prefill + KV cache optimized for low-latency inference
This is the direction of on-device AI agents — small, fast, deeply integrated with the OS.