PulseGateIndexCategoriesUpdatesLive intelligence on AI-era software— indexed in the last hour
Coverage—projects tracked
Freshness—newest entry
Cadence—last week average · — today
Index9 markets86 categories
PulseGate

Live intelligence on the AI-era software market — apps, models, agents and infrastructure.

Most of it never reaches an official store. PulseGate maps the whole market — every category, worldwide — and measures how it moves: what’s launching, what’s gaining, what’s going quiet.

FollowGitHubX (Twitter)LinkedIn
Platform
All AppsFull IndexCategoriesIndustry UpdatesData SourcesCoverage RulesGlossaryEmbed Widget
Support
Help CenterSubmit your projectReport an Issue
Company
AboutDimaxiaPress & DataContactPlatform Status
Legal
PrivacyTermsDisclaimer
Dimaxia · Dymaxio s.r.o. · Prague, Czechia · © 2026WatchlistSitemapSystem status
PulseGateMVMiniCPM V 2
Visit↗
Skip to content
  1. Index›
  2. Foundation models & chat›
  3. MiniCPM V 2
← Back to the index
MV

MiniCPM V 2

huggingface.co·Infrastructure

MiniCPM-V-2 is an open-source vision-language model from OpenBMB designed for visual question answering and general multimodal tasks. It combines strong language understanding with visual processing capabilities and is distributed on Hugging Face with Transformers support. The model is optimized for efficiency while maintaining high performance on benchmarks like ScreenSpot-Pro, making it suitable for research and local deployment.

Open SourceApache-2.0WebCLIAPI
MMiniCPM V 2 preview
Visit huggingface.co↗
26.0kstars
2.0kforks
4alternatives
3features
2024since

Overview

3 features

MiniCPM V 2 is a Foundation models & chat project. It focuses on enabling efficient on-device or local multimodal AI that can understand images and answer questions about them. It is built as an open-source project for AI researchers and developers. The project is open source (Apache-2.0). It ships for the web, the command line, and API.

Behind MiniCPM V 2 is OpenBMB, and it first shipped in 2024. The project is developed in the open on GitHub with 26k stars and 26 commits in the last 90 days. Key capabilities include Visual Question Answering, Multimodal Understanding, and Transformers Compatible.

Summary written by a language model from the project’s public pages.

  • ✓Visual Question Answering
  • ✓Multimodal Understanding
  • ✓Transformers Compatible
Tags
multimodal-llmvision-language-modelvisual-qaminicpmopenbmb
AI capabilities
Multimodal
Inference: LocalWeights: Open

Built with & integrations

Hosting
AWS
AI providers
local_ossmeta_llama
Runs on
BrowserCLIAPI-only
Detected from
AWS
x-amz-cf-id header · x-amz-cf-pop header · via header
local_oss
bollama in the HTML · bvllm in the HTML · huggingface in the HTML
meta_llama
llama- in the HTML

Trust & compliance

License
Apache-2.0
Verified signals
✓HTTPS✓Open Source✓Free tier✓GitHub · ★ 26.0k✓Active maintenance

Indexing history

1

What PulseGate has recorded for this listing

  1. Indexed22 Jul · 13:53 UTC
    openbmb/MiniCPM-V-2 verified against its public source
    Source: PulseGate · Open ↗

Frequently asked questions about MiniCPM V 2

What is MiniCPM V 2?
MiniCPM V 2 focuses on enabling efficient on-device or local multimodal AI that can understand images and answer questions about them. It is catalogued under Foundation models & chat on PulseGate.
Who is MiniCPM V 2 for?
MiniCPM V 2 is an open-source project built for AI researchers and developers.
Is MiniCPM V 2 free?
Yes — MiniCPM V 2 is open source under the Apache-2.0 license and free to use.
What platforms does MiniCPM V 2 run on?
MiniCPM V 2 runs on the web, the command line, and API.
Is MiniCPM V 2 still maintained?
The GitHub repository shows 26 commits in the last 90 days.
What projects are similar to MiniCPM V 2?
Similar projects tracked by PulseGate include Gpt Oss 120b, Ouro 1.4B, and Mistral Nemo Instruct 2407 W8A8 Dynamic Per Token.Gpt Oss 120bOuro 1.4BMistral Nemo Instruct 2407 W8A8 Dynamic Per Token
Who develops MiniCPM V 2?
MiniCPM V 2 is developed by OpenBMB.
How long has MiniCPM V 2 been around?
MiniCPM V 2 first shipped in 2024.

At a glance

Pricing
Open Source
Platforms
Cli · Web
Languages
English
Open source
Yes · ★ 26.0k
License
Apache-2.0
Built for
AI researchers and developers
Model
Open source
Solves
Enabling efficient on-device or local multimodal AI that can understand images and answer questions about them.

Registered as

GitHub
OpenBMB/MiniCPM-V
Hugging Face
openbmb/MiniCPM-V-2

Developer

OpenBMB
Community-driven
↗ GitHub

Open source

View on GitHub →
Stars
25,974
Forks
2,035
Open issues
57
Last commit
25 Jun 2026
Commits 90d
26
Contributors
36
Authorship
Community-driven
Default branch
main
Latest release
20250527 · 27 May 2025

Live coverage

Identity confidence
Medium · 70.4
Indexed
22 Jul 2026
Lifecycle
Alive
Last seen
22 Jul 2026
Identity audit (13)
Slug
openbmb-minicpm-v-2-huggingface-co
Lifecycle state recorded
22 Jul 2026
Verification state
Indexed for public listing
Listing state
Listed: yes
Index status
Included in index
Latest evidence snapshot
22 Jul 2026
Timeline basis
Indexed-at chronology. This listing's first-seen date was written by the catalog backfill, not observed here, so it is not treated as a sighting.
Name from
Derived from the project's own page and URL.
Category from
Derived from the model's own Hugging Face metadata.
Summary from
Written by a language model from public pages.
Languages from
Detected by a language model from page content.
Last updated
2 Aug 2026
Canonical URL
https://huggingface.co/openbmb/MiniCPM-V-2

Ship this? Send a correction — no account, and you get a link to follow it.

Also in Foundation models & chat

Same category — not a similarity match

  • GOGpt Oss 120bhuggingface.co
  • O1Ouro 1.4Bhuggingface.co
  • MNMistral Nemo Instruct 2407 W8A8 Dynamic Per Tokenhuggingface.co
  • BRBge Reranker V2 M3 Kohuggingface.co
  • Q7Qwen 72Bhuggingface.co
  • MVMiMo V2 Flashhuggingface.co