---
title: "OpenBMB releases MiniCPM5-2B, an efficient open on-device model"
url: https://www.parallelquant.com/posts/openbmb-releases-minicpm5-2b-an-efficient-open-on-device-model-a39abd
source_name: "MarkTechPost"
source_url: https://www.marktechpost.com/2026/09/07/openbmb-releases-minicpm5-2b-a-2-52b-dense-model-averaging-53-9-across-34-benchmarks-and-built-to-run-on-device/
published: 2026-09-07T19:18:07.000Z
topics: ["open source", "llms"]
publisher: "Parallel Quant"
---

# OpenBMB releases MiniCPM5-2B, an efficient open on-device model

*2026-09-07 · Source: [MarkTechPost](https://www.marktechpost.com/2026/09/07/openbmb-releases-minicpm5-2b-a-2-52b-dense-model-averaging-53-9-across-34-benchmarks-and-built-to-run-on-device/)*

OpenBMB released MiniCPM5-2B, a 2.52-billion-parameter dense language model with a 131,072-token context window. It averages 53.9 across 34 benchmarks, ahead of Qwen3.5-4B's 51.1, with its strongest gains in tool use, coding agents, and long-context retrieval. The weights, training data, and intermediate checkpoints are released under Apache 2.0, with GGUF builds starting at 1.56GB.

**Why it matters:** A 2.5B model beating a larger 4B competitor while running on-device continues the trend of small open models closing the gap with flagship-scale systems. Releasing full training data and intermediate checkpoints, not just final weights, gives researchers rare visibility into how the distillation and RL pipeline actually works rather than just the end result.

**Topics:** open source, llms

---
Read the original: https://www.marktechpost.com/2026/09/07/openbmb-releases-minicpm5-2b-a-2-52b-dense-model-averaging-53-9-across-34-benchmarks-and-built-to-run-on-device/
Canonical: https://www.parallelquant.com/posts/openbmb-releases-minicpm5-2b-an-efficient-open-on-device-model-a39abd
Published by Parallel Quant — https://www.parallelquant.com