home.social

#minicpm — Public Fediverse posts

Live and recent posts from across the Fediverse tagged #minicpm, aggregated by home.social.

  1. Firethering @[email protected] ·

    MiniCPM Desk Pet turns the MiniCPM AI model into a desktop companion that lives alongside your workflow. Install the app, follow the setup wizard, and within a few minutes you can chat with a local AI pet directly from a floating desktop bubble.

    Conversations run on your machine using the local model. The pet can stay visible while you work, react to activity from tools like Cursor, Claude Code, and Codex.

    firethering.com/minicpm-desk-p
    #minicpm #coding #opensource #ai #claudecode #developers

    #minicpm #coding #opensource #ai #claudecode #developers
  2. Firethering @[email protected] ·

    MiniCPM Desk Pet turns the MiniCPM AI model into a desktop companion that lives alongside your workflow. Install the app, follow the setup wizard, and within a few minutes you can chat with a local AI pet directly from a floating desktop bubble.

    Conversations run on your machine using the local model. The pet can stay visible while you work, react to activity from tools like Cursor, Claude Code, and Codex.

    firethering.com/minicpm-desk-p
    #minicpm #coding #opensource #ai #claudecode #developers

    #minicpm #coding #opensource #ai #claudecode #developers
  3. Firethering @[email protected] ·

    MiniCPM Desk Pet turns the MiniCPM AI model into a desktop companion that lives alongside your workflow. Install the app, follow the setup wizard, and within a few minutes you can chat with a local AI pet directly from a floating desktop bubble.

    Conversations run on your machine using the local model. The pet can stay visible while you work, react to activity from tools like Cursor, Claude Code, and Codex.

    firethering.com/minicpm-desk-p
    #minicpm #coding #opensource #ai #claudecode #developers

    #minicpm #coding #opensource #ai #claudecode #developers
  4. Firethering @[email protected] ·

    MiniCPM Desk Pet turns the MiniCPM AI model into a desktop companion that lives alongside your workflow. Install the app, follow the setup wizard, and within a few minutes you can chat with a local AI pet directly from a floating desktop bubble.

    Conversations run on your machine using the local model. The pet can stay visible while you work, react to activity from tools like Cursor, Claude Code, and Codex.

    firethering.com/minicpm-desk-p
    #minicpm #coding #opensource #ai #claudecode #developers

    #developers #claudecode #ai #opensource #coding #minicpm
  5. Firethering @[email protected] ·

    MiniCPM Desk Pet turns the MiniCPM AI model into a desktop companion that lives alongside your workflow. Install the app, follow the setup wizard, and within a few minutes you can chat with a local AI pet directly from a floating desktop bubble.

    Conversations run on your machine using the local model. The pet can stay visible while you work, react to activity from tools like Cursor, Claude Code, and Codex.

    firethering.com/minicpm-desk-p
    #minicpm #coding #opensource #ai #claudecode #developers

    #minicpm #coding #opensource #ai #claudecode #developers
  6. Firethering @[email protected] ·

    MiniCPM5-1B Shows Why the Small-Model Race Isn’t Over
    firethering.com/minicpm5-1b-sm

    #ai #llm #minicpm #genai #opensource #openweights #technews #tech

    #ai #llm #minicpm #genai #opensource #openweights
  7. Firethering @[email protected] ·

    MiniCPM5-1B Shows Why the Small-Model Race Isn’t Over
    firethering.com/minicpm5-1b-sm

    #ai #llm #minicpm #genai #opensource #openweights #technews #tech

    #ai #llm #minicpm #genai #opensource #openweights
  8. Firethering @[email protected] ·

    MiniCPM5-1B Shows Why the Small-Model Race Isn’t Over
    firethering.com/minicpm5-1b-sm

    #ai #llm #minicpm #genai #opensource #openweights #technews #tech

    #ai #llm #minicpm #genai #opensource #openweights
  9. Firethering @[email protected] ·

    MiniCPM5-1B Shows Why the Small-Model Race Isn’t Over
    firethering.com/minicpm5-1b-sm

    #ai #llm #minicpm #genai #opensource #openweights #technews #tech

    #tech #technews #openweights #opensource #genai #minicpm
  10. Firethering @[email protected] ·

    MiniCPM5-1B Shows Why the Small-Model Race Isn’t Over
    firethering.com/minicpm5-1b-sm

    #ai #llm #minicpm #genai #opensource #openweights #technews #tech

    #ai #llm #minicpm #genai #opensource #openweights
  11. H@R0👨🏻‍💻 @[email protected] ·

    最近的小模型可以這麼小？ 想知道它能做到甚麼，與qwen3.5 9b比較有多大差異？

    github.com/openbmb/minicpm

    #minicpm

    #minicpm
  12. H@R0👨🏻‍💻 @[email protected] ·

    最近的小模型可以這麼小？ 想知道它能做到甚麼，與qwen3.5 9b比較有多大差異？

    github.com/openbmb/minicpm

    #minicpm

    #minicpm
  13. Some(oz) @[email protected] ·

    Me resigno a pagar OpenAI, o otro LLM, porque no tengo un servidor lo suficiente potente donde correr MiniCPM-V con Ollama.

    Este modelo es "ligero" pero se traga 4GB de memoria de todos modos, y corre mucho mejor si tiene acceso a un GPU. En este contexto son más económicas las APIs de OpenAI o Anthropic.

    Creo que para extraer datos de una imagen pequeña, será gratis o cerca de 0 de todos modos, pero perfiero no depender de servicios externos. 🤔

    #ollama #minicpm

    #ollama #minicpm
  14. Some(oz) @[email protected] ·

    Me resigno a pagar OpenAI, o otro LLM, porque no tengo un servidor lo suficiente potente donde correr MiniCPM-V con Ollama.

    Este modelo es "ligero" pero se traga 4GB de memoria de todos modos, y corre mucho mejor si tiene acceso a un GPU. En este contexto son más económicas las APIs de OpenAI o Anthropic.

    Creo que para extraer datos de una imagen pequeña, será gratis o cerca de 0 de todos modos, pero perfiero no depender de servicios externos. 🤔

    #ollama #minicpm

    #ollama #minicpm
  15. Some(oz) @[email protected] ·

    Me resigno a pagar OpenAI, o otro LLM, porque no tengo un servidor lo suficiente potente donde correr MiniCPM-V con Ollama.

    Este modelo es "ligero" pero se traga 4GB de memoria de todos modos, y corre mucho mejor si tiene acceso a un GPU. En este contexto son más económicas las APIs de OpenAI o Anthropic.

    Creo que para extraer datos de una imagen pequeña, será gratis o cerca de 0 de todos modos, pero perfiero no depender de servicios externos. 🤔

    #ollama #minicpm

    #ollama #minicpm
  16. Some(oz) @[email protected] ·

    Me resigno a pagar OpenAI, o otro LLM, porque no tengo un servidor lo suficiente potente donde correr MiniCPM-V con Ollama.

    Este modelo es "ligero" pero se traga 4GB de memoria de todos modos, y corre mucho mejor si tiene acceso a un GPU. En este contexto son más económicas las APIs de OpenAI o Anthropic.

    Creo que para extraer datos de una imagen pequeña, será gratis o cerca de 0 de todos modos, pero perfiero no depender de servicios externos. 🤔

    #ollama #minicpm

    #minicpm #ollama
  17. Alexander Gerber @[email protected] ·

    Zur Einordnung:
    "[...] Kombination aus kleineren Modellen und lokaler Datenverarbeitung die Kosten senkt und den Schutz der #Privatsphäre verbessert.

    Das neueste Modell von #Modelbest, #MiniCPM 3.0, hat
    NUR
    vier #Milliarden #Parameter, erreicht aber bei verschiedenen Benchmarks die Leistung des alten #chatgpt35."

    t3n.de/news/was-kommt-nach-dee

    #privatsphare #modelbest #minicpm #milliarden #parameter #chatgpt35
  18. Dr. Fortyseven 🥃 █▓▒░ @[email protected] ·

    Good ol' Squeaky Pete.

    #llm #minicpm

    #llm #minicpm
  19. Dr. Fortyseven 🥃 █▓▒░ @[email protected] ·

    Good ol' Squeaky Pete.

    #llm #minicpm

    #llm #minicpm
  20. Dr. Fortyseven 🥃 █▓▒░ @[email protected] ·

    Good ol' Squeaky Pete.

    #llm #minicpm

    #llm #minicpm
  21. Dr. Fortyseven 🥃 █▓▒░ @[email protected] ·

    Good ol' Squeaky Pete.

    #llm #minicpm

    #minicpm #llm
  22. Dr. Fortyseven 🥃 █▓▒░ @[email protected] ·

    Good ol' Squeaky Pete.

    #llm #minicpm

    #llm #minicpm
  23. OpenBMB @[email protected] ·
    🚀 Exciting news! MiniCPM3-4B is here! 🎉 ✨ Outperforms Phi-3.5-mini-instruct & GPT-3.5-Turbo 🔥 Matches the performance of larger models like Llama3.1-8B-Instruct & Qwen2-7B-Instruct 🔗 GitHub: https://t.co/zaffsLsx5m 🤗 HuggingFace: https://t.co/5ERlyJBviH Key features: 🛠️ Function Call & 💻 Code Interpreter 🧮 Exceptional reasoning and mathematical abilities 🌍 Seamless multilingual support (English & Chinese) 📜 Long Context Capability: Natively supports a 32k context length with flawless performance, leveraging the LLM x MapReduce approach to theoretically handle infinite context lengths. 🔍 RAG capabilities with MiniCPM RAG Suite #AI #NLP #MiniCPM #LLM
    #ai #llm #nlp #minicpm
  24. OpenBMB @[email protected] ·
    🚀Introducing MiniCPM-V 2.6! 🔥 1、Surpassing GPT-4V in single image, multi-image and video understanding 📸🎥 2、Outperforms GPT-4o mini and Gemini 1.5 on OpenCompass 🏆 3、Real-time video analysis on iPad 📱💨 Try out the best on-device multimodal LLM here！ 👑 GitHub：https://t.co/iYDxpa52tn Huggingface：https://t.co/KNuLqj2Vp6 #MLLM #MiniCPM
    #mllm #minicpm
  25. Banana Pi Open Source Hardware @[email protected] ·

    #BananaPi BPI-F3 Now this is the model of #ChatGLMTV2-6b, the model size is 3.6G, the performance is 0.7t/s in Chinese, 1.3T/s in English.such as #minicpm, #qwen2, #phi3, #llama3, #qwen1.5, #chatglm, etc.
    forum.banana-pi.org/t/bpi-f3-l
    #ai #llm

    #bananapi #chatglmtv2 #minicpm #qwen2 #phi3 #llama3
  26. Banana Pi Open Source Hardware @[email protected] ·

    #BananaPi BPI-F3 Now this is the model of #ChatGLMTV2-6b, the model size is 3.6G, the performance is 0.7t/s in Chinese, 1.3T/s in English.such as #minicpm, #qwen2, #phi3, #llama3, #qwen1.5, #chatglm, etc.
    forum.banana-pi.org/t/bpi-f3-l
    #ai #llm

    #bananapi #chatglmtv2 #minicpm #qwen2 #phi3 #llama3
  27. Banana Pi Open Source Hardware @[email protected] ·

    #BananaPi BPI-F3 Now this is the model of #ChatGLMTV2-6b, the model size is 3.6G, the performance is 0.7t/s in Chinese, 1.3T/s in English.such as #minicpm, #qwen2, #phi3, #llama3, #qwen1.5, #chatglm, etc.
    forum.banana-pi.org/t/bpi-f3-l
    #ai #llm

    #bananapi #chatglmtv2 #minicpm #qwen2 #phi3 #llama3
  28. Banana Pi Open Source Hardware @[email protected] ·

    #BananaPi BPI-F3 Now this is the model of #ChatGLMTV2-6b, the model size is 3.6G, the performance is 0.7t/s in Chinese, 1.3T/s in English.such as #minicpm, #qwen2, #phi3, #llama3, #qwen1.5, #chatglm, etc.
    forum.banana-pi.org/t/bpi-f3-l
    #ai #llm

    #llm #ai #chatglm #qwen1 #llama3 #phi3