Footer

Your go-to destination for discovering trending open-source projects and uncovering the insights that matter

Legal

  • Terms and conditions
  • Privacy policy

More

  • Pricing
  • Advertise
  • onedump
  • gosnakego
  • Contact us

Social

  • X (Twitter)
  • GitHub
Trendshift owl
What they build speaks louder than words
© 2026 Trendshift, created by Julian Li with ❤️
SignalAdvertise
Trendshift
SignalAdvertise
Sign in
Trendshift owl

Discover trends that matter

SignalAdvertise
DailyWeeklyMonthlyYearly
Live mentionsTopics
RepositoriesDevelopers
InsightsStats

It's a plan
It's a plan
Trina AX
Trina AX
Bifrost
Bifrost
OfinTech Desk
OfinTech Desk
Busbar
Busbar
Omnigraph
Omnigraph

OpenBMB/MiniCPM-V

See, hear, and interact on your local devices.

#Language model
Visit GitHub
Python
27.2k
2.2k
28 contributors
Apache License 2.0
AchievementsView all →
FeaturedAdvertise to 180K+ monthly visitors
It's a plan

Open-source Linear alternative

An issue tracker where AI agents take the work you assign them

Trina AX

A self-hosted team AI workspace for company files, with per-person folder permissions

Bifrost

Fastest Enterprise AI Gateway for Routing, Governing, and Securing all your AI Traffic

OfinTech Desk

An open-source AI workspace for finance and accounting teams, in which every figure is traced to its source

Busbar

Control what AI can do before it acts

Omnigraph

Versioned graph database on object storage. Git-style workflows and multimodal retrieval

Momentum

How fast OpenBMB/MiniCPM-V is gaining stars, and where it lands on Trendshift and GitHub Trending

Activity and trending

Stars, forks and merged pull requests each day or month, lined up with the repository's rank on Trendshift Trending

Sep 23 – Nov 22, 2026

Stars +734 in 61 days

050100150
114

Forks +83 in 61 days

0510
8

Merged PRs 6 in 61 days

0123
3

Trendshift Trendingwhere the repository ranked each day it made the top 25

Not in the Trendshift top 25 in this period

Sep 23Oct 1Oct 9Oct 17Oct 25Nov 2Nov 10Nov 18
The left and right arrow keys step from day to day; Home and End go to the first and the last

Stars, forks, merged pull requests and Trendshift Trending rank, by day
DayStars gainedForks gainedMerged PRs
Wed, Sep 23, 2026+6+00
Thu, Sep 24, 2026+5+10
Fri, Sep 25, 2026+3+00
Sat, Sep 26, 2026+1+00
Sun, Sep 27, 2026+2+00
Mon, Sep 28, 2026+8+30
Tue, Sep 29, 2026+7+10
Wed, Sep 30, 2026+5+00
Thu, Oct 1, 2026+2+00
Fri, Oct 2, 2026+5+00
Sat, Oct 3, 2026+4+00
Sun, Oct 4, 2026+2+00
Mon, Oct 5, 2026+3+00
Tue, Oct 6, 2026+0+00
Wed, Oct 7, 2026+3+10
Thu, Oct 8, 2026+11+40
Fri, Oct 9, 2026+8+10
Sat, Oct 10, 2026+8+20
Sun, Oct 11, 2026+4+10
Mon, Oct 12, 2026+31+30
Tue, Oct 13, 2026+114+73
Wed, Oct 14, 2026+72+81
Thu, Oct 15, 2026+36+10
Fri, Oct 16, 2026+15+20
Sat, Oct 17, 2026+29+30
Sun, Oct 18, 2026+18+40
Mon, Oct 19, 2026+31+50
Tue, Oct 20, 2026+26+80
Wed, Oct 21, 2026+24+30
Thu, Oct 22, 2026+20+20
Fri, Oct 23, 2026+7+20
Sat, Oct 24, 2026+8+00
Sun, Oct 25, 2026+8+11
Mon, Oct 26, 2026+6+00
Tue, Oct 27, 2026+8+00
Wed, Oct 28, 2026+19+10
Thu, Oct 29, 2026+14+10
Fri, Oct 30, 2026+17+01
Sat, Oct 31, 2026+7+30
Sun, Nov 1, 2026+2+10
Mon, Nov 2, 2026+6+00
Tue, Nov 3, 2026+16+10
Wed, Nov 4, 2026+0+10
Thu, Nov 5, 2026+8+00
Fri, Nov 6, 2026+10+00
Sat, Nov 7, 2026+2+00
Sun, Nov 8, 2026+13+20
Mon, Nov 9, 2026+19+40
Tue, Nov 10, 2026+10+50
Wed, Nov 11, 2026+6+00
Thu, Nov 12, 2026+4+00
Fri, Nov 13, 2026+7+00
Sat, Nov 14, 2026+7+00
Sun, Nov 15, 2026+1+00
Mon, Nov 16, 2026+5+00
Tue, Nov 17, 2026+6+00
Wed, Nov 18, 2026+3+10
Thu, Nov 19, 2026+3+00
Fri, Nov 20, 2026+3+00
Sat, Nov 21, 2026+4+00
Sun, Nov 22, 2026+2+00
Total+734+836
  • 1#1 on the list
  • 7Rank that day
  • Not trending
1

GitHub trending history

Where the repository ranked on GitHub Trending, one dot for each day it was on a list

Apr 15, 2024 – Feb 8, 2026#1 on 6 days

#1#5#10#15#20#25
Top 10
May 2024AugNovFebMayAugNovFeb
The left and right arrow keys step from day to day; Home and End go to the first and the last

Mentions and achievements

Where people are talking about OpenBMB/MiniCPM-V, and every badge it has earned
  1. Nov 191 post
    • MiniCPM-V 4.7 的手机演示给了 13+ tokens/s。验手机扫一页文档,还要从提交计时到字段全部返回。 用同一页扫描件分别跑 1B 和 35B-A3B,记录首字耗时、整页用时和漏掉的字段。还要记设备、权重版本和峰值内存。

      Read full on X, posted by @CrisSL0617

      @CrisSL0617 · x.com

  2. 1 month earlier
  3. Oct 162 posts
    • 🚨 @OpenBMB just dropped MiniCPM-V 4.7, and the engineering behind it is seriously impressive. 35B total parameters, ~3B active at inference, and ~3GB memory in its target on-device configuration.…

      Read full on X, posted by @DataChaz

      @DataChaz · x.com

    • 4/ This already reaches beyond desktop GPUs. MiniCPM-V 4.7 comes in two sizes: the 1B used above, and 35B-A3B, the series' first MoE model. On an iPhone 17 Pro Max, the 35B-A3B card reports 13+…

      Read full on X, posted by @heyshrutimishra

      @heyshrutimishra · x.com

  4. Oct 152 posts
    • 云端拼参数的仗还没打完,端侧先把 35B 装进口袋了 MiniCPM-V 4.7 今天发布,国产开源多模态 35B 的个头只占约 3GB 内存,iPhone 17 Pro Max 跑到 13 tokens/秒 权重、推理代码、微调代码全公开

      Read full on X, posted by @ai_fengshou

      @ai_fengshou · x.com

    • 【每天模型点评】3B 模型做决策,一个 token 都不输出,8 毫秒一次 🤯 这两周最新开源小模型 Top 4: 1️⃣ 腾讯 Youtu-Parsing-Omni(5B)文档/图表/音视频统一转 JSON 2️⃣ Liquid d1-3B 零输出 token 的决策模型 3️⃣ LightOnOCR-3(4B,Apache 2.0)带坐标定位的 OCR 4️⃣ MiniCPM-V…

      Read full on X, posted by @M_NU11

      @M_NU11 · x.com

  5. Oct 142 posts
    • openbmb just put a 35b multimodal moe on phones. minicpm-v 4.7 35b-a3b (the a3b means ~3b params active per token). with lookahead expert scheduling, openbmb reports 13+ tokens/s on an iphone 17 pro…

      Read full on X, posted by @trivediprateek

      @trivediprateek · x.com

    • 手机上跑三百五十亿参数的多模态模型 面壁智能开源了新一代端侧模型,用提前预取专家权重的办法,只占约3GB内存就能跑,在iPhone 17 Pro Max上每秒生成13个以上词元,还有1B的轻量版~ #开源 #端侧AI

      Read full on X, posted by @zhuxiaoniu77

      @zhuxiaoniu77 · x.com

  6. Oct 133 posts
    • A 1B AI Model on an Old OnePlus 8 Pro—and the Case for PocketAI A six-year-old OnePlus 8 Pro just gave me a glimpse of what PocketAI could look like. I ran OpenBMB's MiniCPM-V 4.7 1B, a…

      Read full on X, posted by @jalam1001

      @jalam1001 · x.com

    • A 35B model on a phone. 3GB of RAM, 13+ tokens/s on an iPhone 17 Pro Max. OpenBMB's MiniCPM-V 4.7: open weights, 3B active. Experts preload a layer ahead, so it barely stalls. They claim 5x faster on…

      Read full on X, posted by @DracoVibeCoding

      @DracoVibeCoding · x.com

    • 今天上新的模型Meta的Muse Wonder、智谱的GLM-Legal中,面壁开源的MiniCPM-V 4.7值得一看,端侧多模态的部署经济学被改写了 MiniCPM-V 4.7 35B-A3B用量化压缩+LES调度,实现了手机跑35B MoE,推理速度达到每秒十几个Token…

      Read full on X, posted by @aigclink

      @aigclink · x.com

You might also like

Repositories close to OpenBMB/MiniCPM-V
FeaturedAdvertise to 180K+ monthly visitors
OfinTech Desk

An open-source AI workspace for finance and accounting teams, in which every figure is traced to its source

Trina AX

A self-hosted team AI workspace for company files, with per-person folder permissions

Busbar

Control what AI can do before it acts

Omnigraph

Versioned graph database on object storage. Git-style workflows and multimodal retrieval

It's a plan

Open-source Linear alternative

An issue tracker where AI agents take the work you assign them

Bifrost

Fastest Enterprise AI Gateway for Routing, Governing, and Securing all your AI Traffic

OpenBMB/MiniCPM-V-Apps

Swift

MiniCPM-V apps — fully offline multimodal chat on iOS / Android / HarmonyOS

533112

QwenLM/Qwen3-Omni

Jupyter Notebook

Qwen3-omni is a natively end-to-end, omni-modal LLM developed by the Qwen team at Alibaba Cloud, capable of understanding text, audio, images, and video, as well as generating speech in real time.

4.1k327

Meituan-AutoML/MobileVLM

Python

Strong and Open Vision Language Assistant for Mobile Devices

1.4k92

QwenLM/Qwen2.5-Omni

Jupyter Notebook

Qwen2.5-Omni is an end-to-end multimodal model by Qwen team at Alibaba Cloud, capable of understanding text, audio, vision, video, and performing real-time speech generation.

4.1k342

deepseek-ai/DeepSeek-VL

Python

DeepSeek-VL: Towards Real-World Vision-Language Understanding

4.2k615

zai-org/CogVLM2

Python

GPT4V-level open-source multi-modal model based on Llama3-8B

2.4k166

OpenBMB/MiniCPM-o-Demo

Python

Official PyTorch+CUDA Full-functional Web Demo for MiniCPM-o 4.5

43688

jingyaogong/minimind-o

Python

🎙️ A 0.1B Omni model trained from scratch, capable of listening, speaking, and seeing!

2.8k370

moonlin1213/cove-sensory-mcp

Python

Give text-only LLMs eyes and ears through a privacy-safe local MCP server.

12327