OpenBMB ✓

@OpenBMB

OpenBMB (Open Lab for Big Model Base) aims to build foundation models and systems towards AGI. Connect with us: https://t.co/N9pevTnoOa

10 510Followers

379Following

1 519Posts total

671.8KViews on collected posts

Postingan terbaru

OpenBMB ✓@OpenBMB7 Sep

@OpenBMB @ArtificialAnlys Congrats on the launch! Run MiniCPM5-2B on RTX PRO 6000, RTX 5090, and DGX Spark with SGLang 🫡 https://t.co/NxwNjoU5d8 2.1K views · 30 likes · 1 reposts · 2 replies Open on X →

OpenBMB ✓@OpenBMB7 Sep

@OpenBMB Weights are the teaser. Opening data, recipes, and the RL stack is the actual “open” claim — funeral and birth certificate in one thread. 188 views · 1 likes · 0 reposts · 0 replies Open on X →

OpenBMB ✓@OpenBMB7 Sep

MiniCPM5-2B is already Day-0 adapted across: 💻 Intel — Core Ultra + OpenVINO 📱 Arm — Armv9 + SME2 ⚙️ Rockchip — RK3588 + RK1828 On mobile devices with Arm SME2, MiniCPM5-2B delivers around 1.7× higher prefill performance and 1.2× higher decode performance. It also supports 6.2K views · 90 likes · 4 reposts · 3 replies Open on X →

OpenBMB ✓@OpenBMB7 Sep

We’re not just releasing the model weights. We’re opening up the data, training recipes, and RL stack behind MiniCPM5-2B: 📊 Data UltraData-Code · ~550B tokens UltraData-SFT-Agent-2609 · ~500K samples UltraData-RL-2609 · 80K+ samples UltraX · ~100B tokens / 114M samples ⚙️ https

12.5K views · 130 likes · 14 reposts · 5 replies Open on X →

OpenBMB ✓@OpenBMB7 Sep

Across 34 benchmarks covering coding, math, instruction following, general knowledge, long-context understanding, tool use, and agentic tasks, MiniCPM5-2B achieves an average score of 53.9, ranking #1. It outperforms the second-ranked 2B model at 33.2, as well as the https://t.c

8.8K views · 62 likes · 1 reposts · 2 replies Open on X →

OpenBMB ✓@OpenBMB7 Sep

2B parameters doesn’t mean 2B-level capability. With a similar token budget: 21K tokens (14K thinking + 7K answer) → MiniCPM5-2B 19K tokens (12K thinking + 7K answer) → Granite 4.2 3B 21K tokens (14K thinking + 7K answer) → LFM2.5-2.6B 2B parameters. Higher intelligence https:/

11.5K views · 67 likes · 1 reposts · 6 replies Open on X →

OpenBMB ✓@OpenBMB7 Sep

🚀 Meet MiniCPM5-2B, a 2B-parameter language model bringing high intelligence density to the edge, now open source! It ranks #1 among open-source models under 4B parameters on the @ArtificialAnlys Intelligence Index, with a score of 23. It also scores 20 on the Agentic Index, ht

630.5K views · 2.3K likes · 318 reposts · 187 replies Open on X →

Dibandingkan akun berukuran sama

7 postingan dari 90 hari terakhir, dibandingkan dengan rentang 10K–100K pengikut. tampil luas, tetapi sedikit penonton yang merespons.

Median tayangan8 847akun ini924median untuk 10K–100K

Jangkauan, %84.18%akun ini3.62%median untuk 10K–100K

Interaksi, %0.75%akun ini1.52%median untuk 10K–100K

Metrik	Akun ini	Median untuk 10K–100K	Rasio
Median tayangan per postingan	8 847	924	9.57×
Jangkauan (tayangan ÷ pengikut)	84.18%	3.62%	23.2×
Tingkat interaksi	0.75%	1.52%	0.49×

Akun lain pada rentang ini → Bandingkan dengan akun lain → Bagaimana tolok ukur ini disusun →

Growth & engagement

How the posts we collected actually performed: views and reaction rate post by post, what the audience did with them, and where the follower count goes.