2B open-source MiniCPM5 tops small-model index, tested as an offline iPhone iMessage agent
SimplyAnnisa · x · 2026-09-13
OpenBMB's MiniCPM5-2B ranks #1 under 4B on the Artificial Analysis Intelligence Index and tops its Agentic Index outright, 20 vs 9 for the next small model — evidence of the Densing Law, where capability density doubles roughly every 3.5 months.
The author went beyond benchmarks and built an iMessage agent with the model running entirely on-device: six tools across eight real-world scenarios, three runs each, handling reminders, calendar events, lookups, and replies without anything leaving the phone. His own results, not official ones, show a 2B model is already useful for pocket-sized private assistants.
Related event: OpenBMB's MiniCPM5-2B tops sub-4B model rankings and runs offline on iPhone(2 posts)→
More from Infra
- Would LITE accepting MRVL's merger offer prove its moat was overstated? — BenBajarin · 2026-10-30
- Claymation body horror on 8GB: three wrong settings, not the GPU, made local renders slow — roro9- · 2026-10-30
- durable-object-migrator: zero-downtime exports for Cloudflare Durable Objects — samgoodwin89 · 2026-10-30
- An unnamed firm already runs a fairly scaled dedicated vehicle for compute lending, says analyst — matt_slotnick · 2026-10-30
- GPU break-even throughput vs open-weight token prices up 25-83% since May — bookwormengr · 2026-10-30
- Sam Altman says the chip supply chain's invisible hand is failing — and DRAM is why — SnoozeDoggyDog · 2026-10-30