OpenBMB releases MiniCPM5-2B: a 2B on-device model with long-context and tool-calling
openbmb · hf · 2026-09-06
OpenBMB has released MiniCPM5-2B on Hugging Face, a 2B text-generation model aimed at on-device and edge deployment.
- Available in transformers and safetensors formats, built on the llama architecture.
- Highlights long-context support and tool-calling, targeting on-device and edge-ai use cases.
Related event: OpenBMB Releases MiniCPM5-2B Open Model for On-Device Use(3 posts)→
More from Models
- One confidence signal controls LLM abstention: 66.5% to 7% in Gemma 3 27B — dejanseo · 2026-09-08
- NVIDIA details how Domyn specializes Nemotron models for regulated industries — NVIDIAAI · 2026-09-08
- V4.1 Flash is ~3x faster than V4-Flash, smarter per token and image-hungry — teortaxesTex · 2026-09-08
- Claude refuses to transcribe TikTok links, revealing platform-specific guardrails — gerardsans · 2026-09-08
- GPT-6 Astra computer use isn't in Chat — the real surfaces are Work, Codex and desktop — socialwithaayan · 2026-09-08
- Scientist finds ChatGPT beats Claude for his coding and data workflows — Chaochic · 2026-09-08