Appreciate you sharing this @AdinaYakup ! 🙌
It’s exciting to see the community’s interest in pushing local multimodal AI forward, from phones to edge devices.
OpenBMB thanks community for interest in edge multimodal AI
AIOpenBMB says it is pleased by community interest in local multimodal AI that runs from phones to edge devices. The post builds on a MiniCPM V4.7 announcement, which claims a 35B-A3B on-device MoE model reaches over 13 tokens per second on an iPhone 17 Pro Max with about 3GB RAM. A 1B ultra-lightweight vision-language model is also included, both are Apache 2.0.
@OpenBMB
Let's start the week with MiniCPM V4.7 from @OpenBMB 🔥 ✨ 35B-A3B: On-device MoE - 35B/ 3B active ⚡️ - 13+ tok/s on iPhone 17 Pro Max with ~3GB RAM - Outperforms Qwen3.6 35B-A3B in overall score AND inference time ✨1B: Ultra-lightweight VLM - Outperforms Qwen3.5 0.8B in BOTH performance & efficiency ✨ Both support: - Image, multi-image & video understanding - Efficient 4×/16× visual token compression - iOS, Android & HarmonyOS - Apache 2.0
Source details
OpenBMB · x.comPublished · added here
Original title: Appreciate you sharing this @AdinaYakup ! 🙌