@AdinaYakup: MiniCPM V4.6 a 1B MLLM that actually runs on your phone, just released by @OpenBMB 1B - Apache2.0 Runs on iOS, Android,…
Summary
OpenBMB has released MiniCPM V4.6, a 1B-parameter multimodal large language model optimized for mobile devices under the Apache 2.0 license. It features mixed visual token compression and claims approximately 1.5x faster throughput than Qwen3.5 0.8B while running natively on iOS, Android, and HarmonyOS.
View Cached Full Text
Cached at: 05/11/26, 04:42 PM
MiniCPM V4.6 🔥 a 1B MLLM that actually runs on your phone, just released by @OpenBMB
✨ 1B - Apache2.0 ✨ Runs on iOS, Android, HarmonyOS ✨ ~1.5× faster throughput than Qwen3.5 0.8B ✨ Mixed 4x/16x visual token compression https://t.co/KBUal2oUf2
Similar Articles
MiniCPM-V 4.6
MiniCPM-V 4.6 is an ultra-efficient 1.3B vision-language model optimized for mobile devices.
@FeitengLi: OpenBMB open-sources MiniCPM-V 4.6, 1.3B parameters (SigLIP2-400M + Qwen3.5-0.8B), 262k context, visual encoding FLOPs 50%+ less than previous generation. Token cost for the same task is lower than Qwen3.5-0…
OpenBMB releases MiniCPM-V 4.6, a 1.3B-parameter multimodal LLM with 262k context and significantly reduced visual encoding FLOPs, achieving strong benchmark performance and broad inference framework support.
MiniCPM4: Ultra-Efficient LLMs on End Devices
MiniCPM4 is a highly efficient large language model designed for end devices, achieving strong performance with 0.5B and 8B parameter versions through innovations in sparse attention, data filtering, training algorithms, and inference systems.
@AdinaYakup: MiniCPM5-1B is an impressive release in the 1B class! @OpenBMB https://huggingface.co/collections/openbmb/minicpm5… 1B …
MiniCPM5-1B is a new 1B parameter AI model from OpenBMB featuring hybrid reasoning with Think/No-Think modes, 128K context, and Apache 2.0 license, running on various hardware.
MiniCPM-V 4.5: Cooking Efficient MLLMs via Architecture, Data, and Training Recipe
MiniCPM-V 4.5 is an 8B multimodal large language model that achieves high efficiency and strong performance through a unified 3D-Resampler architecture, a novel data strategy, and a hybrid reinforcement learning approach. The model reportedly surpasses larger proprietary and open-source benchmarks while significantly reducing GPU memory usage and inference time.