Alibaba's Banma ships AutoOmni 2.0: 3B-active edge model nears 10x-larger cloud models
机器之心 · wechat · 2026-09-24
At the Yunqi Conference, Alibaba's Banma unveiled AutoOmni 2.0-23B-A3B, a 23B-total / 3B-active MoE edge model for smart cockpits. The company claims it matches a 10x-larger cloud model on ordinary cockpit tasks and reaches 80–90% on complex ones. CTO Si Luo admitted that just three weeks earlier he judged a demo impossible within the quarter — edge model progress is outpacing even practitioners' own expectations.
The article frames the second phase of AI-in-cars: hardware is ubiquitous (70.5% L2 penetration in H1 2026) yet paid adoption of higher-level ADAS is below 10% — users value the capability but expect it free. Edge deployment faces three walls (memory, latency, concurrency) plus privacy and cost constraints; Banma's answer combines sparse MoE with quantized deployment (5–6x faster inference, 99%+ quantization fidelity, 50% less memory), a brain/cerebellum split between the AutoOmni model and agent execution framework, SQLite+RAG on-device memory, rejection mechanisms, and a security stack with 98%+ recall against jailbreak attacks.
The strategic read: the battleground is shifting from cloud model capability to the edge; Banma has adapted to ten chip vendors and plans to extend the same execution framework into assisted driving toward cockpit-driving fusion.
More from Embodied
- Uranus: diffusion-based robot simulator hits 24 FPS with open-ended rollout — D-Robotics · 2026-09-24
- Microsoft Open-Sources LIBERO Robot Learning Dataset With 282K Rows on Hugging Face — victormustar · 2026-09-24
- BitRobot to host 3 robotics grand challenges at IROS 2026 with 50+ research teams — micoolcho · 2026-09-24
- Meta reportedly made a keychain just for talking to AI — prasenx · 2026-09-24
- GenRobot releases Gen-HumanEgo: 1,800+ hours of egocentric human data for robot learning — AdinaYakup · 2026-09-24
- TJ-FlyingFish: Chinese team builds 1.6kg amphibious drone that flies and dives for 40 minutes — lukas_m_ziegler · 2026-09-24