Alternatives

Products that do what MiniCPM 4.1 does

The on-device model for your personal data

1. 1
   MiniCPM 4.0▲110

   Ultra-efficient on-device AI, now even faster

   2025

2. 2
   MiniCPM5-1B▲96

   A new SOTA for compact open models on the edge

   May 2026

3. 3
   MiniCPM-V 4.6▲98

   Ultra-efficient 1.3B vision-language model for mobile

   May 2026

4. 4
   MiniCPM-V 4.5▲93

   GPT-4o level vision model on the phone

   2025

5. 5
   MiniMax M2.5▲194

   The first open model to beat Sonnet made for productivity

   Feb 2026

6. 6
   Microsoft Phi-4▲196

   Microsoft’s New Small Language Model For Complex Reasoning

   2024

7. 7
   Open Minis▲91

   An on-device AI Agent that runs on your phone, open & secure

   Aug 2026 · openminis.app

8. 8
   Phi-4-reasoning-vision▲124

   Open-weight 15B multimodal model for thinking and GUI agents

   Mar 2026

9. 9RA
   RentMyCPU – An open-source computational network▲143

   2021 · github.com

10. 10MO
    MicroMDM – Open Source MDM Server for Apple Devices▲146

    2018 · micromdm.io

11. 11
    OpenAI o3 and o4-mini▲142

    Advanced Visual Reasoning & Agentic Tool Use

    2025

12. 12
    GPT Router▲211

    Avoid OpenAI downtimes - one API for 30+ LLMs

    2023

13. 13
    NobodyWho▲106

    Run AI models on any device

    17d ago · github.com

14. 14
    GLM-5▲154

    Open-weights model for long-horizon agentic engineering

    Feb 2026

15. 15
    RunAnywhere▲119

    Ollama but for mobile, with a cloud fallback

    2025

16. 16
    Foundation Models framework▲176

    Build with Apple's on-device AI, now open to developers

    2025

17. 17
    Phi-4-multimodal and Phi-4-mini▲128

    The next generation of the Phi family from Microsoft

    2025

18. 18
    Alpie Core▲177

    A 4-bit reasoning model with frontier-level performance

    Dec 2025

19. 19
    Mu▲126

    Fast, local AI comes to Windows Copilot+ PCs

    2025

20. 20
    ModelPilot▲94

    Optimize Performance, Cost, Speed & Carbon for each prompt

    Nov 2025

21. 21
    Jamba 1.6▲104

    Enterprise-ready, open model with 256K context

    2025

22. 22MF
    Minim – Fast, Flat and File-Based BMS▲8

    2017 · minim.one

23. 23TR
    Try running deep learning inference on Raspberry Pi▲53

    2018 · actcast.io

24. 24MA
    Moondream, a small vision language model that runs on 8GB of RAM▲9

    I've been working on training this small vision language model for the last month - excited to release the first prototype today! It is based on SigLIP (image encoder), Phi-1.5 (text model) and trained using the LLaVa-1.5 training dataset. It runs reasonably fast on CPU with ~8GB of RAM in full 32-bit precision. There's plenty of room to speed it up and reduce memory consumption by quantizing the model. I posted a video of it running on my M2 Macbook Air (on CPU not MPS, so performance should be comparable on other hardware) on Twitter to demonstrate inference speed:…

    2023 · github.com

Ranked by how close each launch is in meaning, then by votes. Refine with a description →