@AdinaYakup: MiniCPM5-1B is an impressive release in the 1B class! @OpenBMB https://huggingface.co/collections/openbmb/minicpm5… 1B …
Summary
MiniCPM5-1B is a new 1B parameter AI model from OpenBMB featuring hybrid reasoning with Think/No-Think modes, 128K context, and Apache 2.0 license, running on various hardware.
View Cached Full Text
Cached at: 05/25/26, 06:43 PM
MiniCPM5-1B is an impressive release in the 1B class! @OpenBMB
https://t.co/1JwnRUYeEW
✨ 1B - Apache 2.0 ✨ Hybrid reasoning with Think / No-Think modes ✨ 128K context ✨ Runs on CPU/Apple Silicon/GPU ✨ Strong eval result in the same size class https://t.co/dnEMpHuaWk
MiniCPM5 - a openbmb Collection
Source: https://huggingface.co/collections/openbmb/minicpm5 updatedabout 5 hours ago
- —
#### openbmb/MiniCPM5-1B Text Generation• 1B• Updatedabout 8 hours ago • 2 • 67 - — #### openbmb/MiniCPM5-1B-SFT Text Generation• 1B• Updatedabout 7 hours ago • 2 • 7
- — https://huggingface.co/spaces/openbmb/MiniCPM5-1B-Demo
- — #### openbmb/MiniCPM5-1B-MLX Text Generation• 0.2B• Updatedabout 8 hours ago • 2
- — #### openbmb/MiniCPM5-1B-GGUF Text Generation• 1B• Updatedabout 8 hours ago • 9
- — #### openbmb/Ultra-FineWeb Viewer• UpdatedDec 10, 2025 • 1.29B • 52.4k • 342
- — #### openbmb/Ultra-FineWeb-L3 Updatedabout 10 hours ago • 115 • 44
- — #### openbmb/UltraData-Math Viewer• UpdatedApr 15 • 181M • 51.4k • 307
Similar Articles
MiniCPM5 1B - what is it?
MiniCPM5-1B is a new small language model from OpenBMB, apparently built from scratch with its own tokenizer and distinct behavior, generating excitement as a capable 1B model.
MiniCPM5-1B
OpenBMB releases MiniCPM5-1B, a dense 1B Transformer model achieving SOTA among open-source 1B-class models, designed for on-device deployment with hybrid reasoning and long-context support.
MiniCPM5-1B Shows Why the Small-Model Race Isn't Over
MiniCPM5-1B is a 1B parameter model from OpenBMB that achieves impressive scores on AIME 2025 and τ2-Bench Telecom, outperforming larger models. It features both fast and reasoning modes from a single checkpoint, enabled by a three-stage post-training process including supervised fine-tuning, reinforcement learning, and on-policy distillation.
@ModelScope2022: MiniCPM5-1B is now fully open source, including weights, training data, and deployment code. 1B params, #1 on Artificia…
MiniCPM5-1B is fully open-sourced with weights, training data, and deployment code; it achieves top scores among sub-2B models and runs on edge devices.
@AdinaYakup: MiniCPM V4.6 a 1B MLLM that actually runs on your phone, just released by @OpenBMB 1B - Apache2.0 Runs on iOS, Android,…
OpenBMB has released MiniCPM V4.6, a 1B-parameter multimodal large language model optimized for mobile devices under the Apache 2.0 license. It features mixed visual token compression and claims approximately 1.5x faster throughput than Qwen3.5 0.8B while running natively on iOS, Android, and HarmonyOS.