AI/TLDR

Sam Witteveen · 2026-09-10 · notable

Sam Witteveen — 'MiniCPM5-2B: The Best Sub-Agent Model Yet?'

Sam Witteveen tests MiniCPM5-2B, OpenBMB's small open model, in an episode posted on 10 September 2026. The walkthrough covers the benchmarks, the training recipe including JustRL II, the model variants and a live demo.

Sam Witteveen video thumbnail for the MiniCPM5-2B walkthrough

Sam Witteveen asks whether MiniCPM5-2B is small enough to run anywhere and still good enough to drive sub-agents.

What is it?

'MiniCPM5-2B: The Best Sub-Agent Model Yet?' went up on Sam Witteveen's channel on 10 September 2026. The episode looks at MiniCPM5-2B, the small open model OpenBMB published on Hugging Face this month, and asks whether something this size can be trusted with the sub-agent jobs normally handed to a much larger model.

How does it work?

The episode is a walkthrough, not a benchmark run. Its own chapter list moves from the benchmarks at 1:06 to the training recipe, spends roughly two and a half minutes on JustRL II, then goes through the MiniCPM5-2B variants and their Hugging Face pages before ending on a live demo at 7:22.

Why does it matter?

Sub-agents are where the bill adds up. A coding or research agent can spawn dozens of small calls in one run, and paying frontier prices for every one of them is what makes agent runs expensive. Testing whether a 2B model holds up in that slot is a cost question, not a curiosity.

Who is it for?

developers building multi-agent systems

Sources · 3 outlets

Tags

  • video
  • sam-witteveen
  • minicpm5-2b
  • openbmb
  • small-models
  • agents
  • reinforcement-learning
  • on-device
  • explainer

← All releases · Learn AI