🚀 Introducing MiniCPM-V 4.7, our new open-source MLLM series! Advancing the Performance–Efficiency Pareto Frontier. It brings strong multimodal capabilities to iOS and Android devices with extreme efficiency. Two new models: 🔹 MiniCPM-V 4.7 35B-A3B — Bring SOTA performance to local devices with newly introduced LES (Lookahead Expert Scheduling) technique, a new milestone of on-device multimodal AI. 🔹 MiniCPM-V 4.7 1B — Lightweight, efficient multimodal AI. Easier to deploy. ⚡ What's new? SOTA performance: Competitive results across 34 benchmarks spanning multimodal understanding, STEM reasoning, OCR and long-video comprehension. Fast on-device inference: LES predicts and preloads expert weights to reduce inference stalls, boosting 5× speedup on iPad Pro M4 (16GB) with byte-for-byte identical outputs. It enables MiniCPM-V 4.7 35B-A3B to achieve 17+ tokens/s on iPad Pro M4 (16GB) and 13+ tokens/s on iPhone 17 Pro Max, while costing only 3GB memory 🤯 Efficient visual processing: 4× and 16× hybrid visual token compression. Even at 16× compression, 35B-A3B scores 90.4 on OCRBench, 5.2 points ahead of Qwen3.6 35B-A3B. Easier customization: We introduce Self-Replay Fine-Tuning, a simple way to customize new target capabilities at low cost while maintaining general performance. Broad hardware support: Day-0 adaptations for Apple, Intel, AMD, Arm and Rockchip, with many more platforms supported through FlagOS! Download, deploy, and build something we haven't imagined yet. 👀👇 🔗 GitHub: github.com/OpenBMB/MiniCPM-V 🤗 Hugging Face: huggingface.co/collections/o…

From data and charts to full reports, running locally. Great to see @aiwithsally putting MiniCPM-V 4.7 to work in an automated reporting workflow. Thanks for sharing the demo!

Great to see community experiments with MiniCPM-V 4.7! Thanks @techNmak for sharing your neo-brutalist portfolio UI. Curious to see what you build next!

100 tok/s, multimodal, and running locally on ~3 GB of memory. 🔥 MiniCPM-V 4.7 makes on-device AI even more practical. Love seeing the @llama_cpp ecosystem make it easy to try!

🚀 MiniCPM-V 4.7 is now supported in vLLM v0.32.0! Thanks @vllm_project for the support. This makes it easier to serve MiniCPM-V 4.7 with high throughput and low latency.

🔱 Why can irrelevant text outrank an image that actually contains the answer? We find that multimodal retrievers can perform well on text-only and image-only corpora, yet degrade sharply when text and images are mixed. We call this phenomenon "Chaos in the Text." Our analysis reveals a systematic Modality Preference: text often receives higher similarity scores than semantically aligned images. We introduce Trident, which jointly trains Text / Image / Fused views with Multi-Positive View InfoNCE. On 6 visual-document retrieval benchmarks, Trident-Qwen3VL-2B improves Mix Avg NDCG@10 from 40.12 → 73.90. 📄 Paper/Project: chaos-in-texts.github.io/ 💻 Code: github.com/OpenBMB/Trident #MultimodalRetrieval #MultimodalRAG #RAG #VLM #Embedding #Trident #ChaosInTheText #OpenBMB

🥈 MiniCPM-V 4.7 just climbed to #2 on @huggingface Trending! Thank you to everyone trying the model, sharing feedback, and building with it. Your support keeps us pushing on-device multimodal AI forward. 📱 35B-A3B MoE runs smoothly on iOS and Android with ~3GB memory. The 1B model delivers strong OCR, math, and video understanding performance. Try it！ 🤗 Models: huggingface.co/collections/o… 💻 GitHub: github.com/OpenBMB/MiniCPM-V Let's keep the momentum going! 🚀

Building ideas with building blocks, powered by on-device AI! 🧱📱✨ Love this creative comparison. Thanks for putting MiniCPM-V 4.7 1B to the test! 🚀

Lisbon, here we come! 🇵🇹✈️ We are heading to Web Summit @WebSummit, Nov 9–12! Come say hi at our booth. Going too ? 👀 Reply or DM us 💬 let’s grab a coffee.☕️ Who’s up for a mini meetup? 🙌🏻 #WebSummit2026

Great to see MiniCPM-V 4.7 on ModelScope! 🚀 Thanks for the support 💙 Excited to make powerful on-device multimodal AI accessible to even more developers!

370 tokens/sec with MiniCPM-V 4.7?! 🔥 Love seeing the community push the limits of what's possible with speculative decoding. Huge shoutout to @Tech2Wild for putting this together! 🚀

Big thanks to @inteldevs for the day-0 support ! 🙌 Excited to bring MiniCPM-V 4.7’s multimodal capabilities to Intel CPUs, GPUs, and NPUs.

🚀 PilotDeck 2.0 is here! Meet the open-source AI Agent Harness built to get complex work done. Developed by Tsinghua THUNLP, @modelbest_ai, @OpenBMB , and AI9Stars, PilotDeck is a model-agnostic Agent operating system that turns natural language instructions into completed tasks — with transparent data flows and the freedom to choose your models. What’s new in 2.0? 📄 End-to-end office work: Create, edit, and verify Word, Excel, and PowerPoint files — not just generate drafts. 🔄 More reliable execution: complex, long-running tasks going through interruptions. Stress-tested with 2,000 interaction messages. 🛠️ Easy to get started: One-click desktop installation and a streamlined setup flow to connect your model and create your workspace. 🔓 Open by design: Fully open-source, model-agnostic, with data flows visible to users. On Workbuddy Bench, PilotDeck scored 79.1 with Qwen3.6-35B-A3B, outperforming WorkBuddy (74.7) and Claude Code (77.3). Build your own AI workspace for the Agent era. 🔗 GitHub: github.com/OpenBMB/PilotDeck Web: pilotdeck.openbmb.cn

Thank you @fahdmirza for the informative tutorial and in-depth review. We really appreciate the time and effort you put into testing and sharing your insights! 🙌

🎬 35B MoE multimodal AI. On your phone. With just 3GB of memory. 🤯 This is MiniCPM-V 4.7 in action: reading real-world signs, planning around constraints, parsing complex documents, and reasoning over visual data. Powered by LES (Lookahead Expert Scheduling), the 35B-A3B model brings efficient MoE inference to mobile devices, while the lightweight 1B variant delivers capable multimodal understanding on resource-constrained hardware. 🛠️ With Self-Replay Fine-Tuning (SRFT), developers can customize models for new tasks while maintaining general performance. From iOS to Android, MiniCPM-V 4.7 makes powerful multimodal AI more practical to run locally. Try it 👇 🔗 github.com/OpenBMB/MiniCPM-V 🤗 huggingface.co/collections/o… Self-Replay Fine-Tuning: openbmb.cn/en/blog/self-repl…

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.

🚀 MiniCPM-V 4.7 is now running on Apple Silicon! Thanks to our partnership with the @Nativ_AI, MiniCPM-V 4.7 (1B & 35B-A3B) now has Day 0 support for fully on-device inference on Mac. With Nativ, you can run: 🧠 MiniCPM-V 4.7-35B-A3B — 35B capability with efficient inference ⚡ MiniCPM-V 4.7-1B — lightweight vision model for edge devices 📷 Image + video understanding 🔒 Fully local — your data stays on your device Tested on Apple Silicon with Nativ v0.4.x: 1B: 24K+ prefill tokens/s, 315 tok/s decode 35B-A3B: 4K+ prefill tokens/s, 90 tok/s decode Bringing powerful multimodal models closer to everyday devices. 🍎 Huge thanks to the Nativ team for making this possible! 🔗 Nativ: github.com/Blaizzy/nativ

💥 MiniCPM-V 4.7 35B-A3B just dropped, and we put it through five real tests on an H100 📱 Open-source MoE built for on-device use, now running on a local GPU 🔹 Setup and serving on a single H100 🔹 Coding: a chimney cake fire simulation 🔹 SQL: find the hidden bug and fix it 🔹 Vision: a handwritten note in three languages 🔹 Physics: reasoning over a page of equations 🔹 Translation: one Brazilian headline into 80 languages 🔥 Full test and honest verdict in the video below 👇 piped.video/zFJiwyhDFrA?si=3DJY… @OpenBMB

Interesting result for local VLMs. MiniCPM-V 4.7 35B-A3B not only used fewer tokens, but also produced a better voxel pagoda than Qwen 3.6 35B-A3. Efficiency + quality is becoming the real battleground for multimodal models.🔥

Great to see MiniCPM-V-4.7-35B-A3B being tested in real agent workflows. 👀 Strong tool use, long context handling, and agent loops are exactly where efficient models need to prove themselves.