Can you imagine a 1.3B-parameter multimodal large model running directly on an iPhone? OpenBMB's latest release, MiniCPM-V 4.6, makes it happen.
This model, open-sourced on May 11, has only 1.3B parameters, yet can handle single-image, multi-image, and video understanding tasks, running smoothly on consumer-grade phones — covering iOS, Android, and HarmonyOS. It's open-sourced under the Apache 2.0 license, and natively supports mainstream inference frameworks like vLLM and SGLang.
Technically, MiniCPM-V 4.6 adopts a combined architecture of SigLIP2-400M vision encoder and Qwen3.5-0.8B language base, supporting context windows up to 262K tokens. Through an early-stage compression mechanism inside the vision encoder, the team reduced compute by over 50%, while providing 4× and 16× compression rate options. On Artificial Analysis benchmarks, the model scores 13, ranking third among open-source models of the same size, well ahead of the median.
The efficiency performance is more critical: compared to Qwen3.5-0.8B, MiniCPM-V 4.6's end-to-end throughput improves by about 1.5×, with cost reduced 19×; even compared to the Qwen3.5-0.8B variant with reasoning thinking, the cost advantage reaches 43×. The quantized version compresses memory demand to 3GB GPU VRAM or about 2GB CPU RAM.
This isn't about challenging GPT-4 or Gemini's position. 1.3B parameters, multimodal, 262K context, video understanding, local execution — these capabilities previously required larger parameter counts, but are now within the compute range of an ordinary phone. For privacy-sensitive applications, offline assistants, or document understanding scenarios, this release means the feasibility frontier of edge AI has been pushed forward significantly.
The model is open-sourced on Hugging Face, with 8 quantized variants and local-deployment reference code available.