Bad Theory Labs has repackaged Liquid AI's LFM2.5-2.6B into a 1.5 GB local Mac Agent called Macaw. The model weights ship as a 4-bit MLX quantization, driving 97 macOS tools (mail, calendar, files, music, system settings) directly from the local model. No network needed, no account required. On an M2, it hit 10/10 tool-call accuracy, a mean 1.21-second response, and 40.3 tokens/second decoding. The code is MIT-licensed, weights live on Hugging Face, and any Apple Silicon machine on macOS 14+ with 8 GB RAM can run it.

What is worth discussing here isn't "yet another on-device AI assistant" — it is three engineering realities this release exposes.

First, a 2.6B model is already enough

LFM2.5 is the hybrid-architecture small model Liquid AI shipped in the second half of 2025, combining on-device inference, long context, and multimodality. What Macaw does on top of it is restrained: no weight fine-tuning, just a system prompt that turns the model's identity into a "Mac control assistant." All other capabilities emerge from prompt-guided tool calling. This trajectory suggests that on-device LLMs in 2026 do not need another round of heavy SFT — as long as the base model's instruction alignment is clean enough, sub-3B models can carry real-world tool orchestration.

Second, 4-bit quantization + MLX is the most stable local-inference stack on Apple Silicon today

BF16 raw weights run around 5 GB, which on an 8 GB Mac mini nearly forces swap. The 4-bit MLX quantization compresses that to 1.5 GB, leaving comfortable headroom for the OS and other apps. Bad Theory Labs released both BF16 and MLX weights — MLX runs on Metal GPU, BF16 falls back to any Transformers backend. This is the smallest working unit behind the 2026 narrative that "consumer hardware can deliver AGI-grade experience."

Third, tool-call accuracy has crossed from "kinda works" to "actually works"

AI benchmarks like BenchLM have long told us that on SWE-Bench and τ-Bench-style Agent leaderboards, frontier models (Claude 4.x, Gemini 3.x, GPT-5.x) still sit roughly 8 months ahead of 7B-30B open-source models. But in Macaw's closed-environment, strict-tool-set scenario, a 2.6B model hits 10/10. The reason is that macOS tools are deterministic APIs — the model never has to read dynamic web content or dodge anti-bot systems. The real stress test for general Agent capability is CUA-style products like Hark Handoff, which force the model to navigate hostile live websites. So the claim "on-device LLMs can already do what Siri cannot" holds — but only when the task boundary is drawn tightly.

Licensing and the commercialization logic

Macaw's biggest constraint is spelled out on its own site: the LFM Open License v1.0 caps commercial use at $10 million in annual revenue. Independent developers, small teams, and hobbyist products can use it freely, but anyone building a commercial product on top will have to renegotiate the license once they cross that revenue threshold. The structure is actually clever — Liquid AI turns the LFM family into the "default base for individual developers" while preserving a separate negotiation window for large customers.

What this leaves for the Chinese AI ecosystem

What is the biggest takeaway Macaw leaves for the Chinese AI scene? The phrase "edge AI" stopped being a marketing slogan in late 2026 and became a deliverable tool. A 1.5 GB weight, zero network, MIT code, install-and-run local Agent — this means that for any indie developer who wants to build a small tool that doesn't depend on cloud APIs, the barrier has dropped to nearly zero. The open question now: when will Apple Intelligence actually upgrade Siri to this level? If the answer is "never," projects like Macaw will eat Siri's market share from below.

Last counter-question: Macaw ships 97 tools today, which sounds enough — yet users will inevitably ask "why doesn't it support mine?" Once personal customization becomes the default expectation, the model itself stops being the moat; tooling depth and OS-integration craft are. In this track, open-source + local + ultra-light will beat "bigger models" over the long run.