1B-parameter dense open-weights language model from OpenBMB for on-device use, with hybrid thinking and 128K context.
Updated EU status checked Last shown
Sources: the vendor's own pages (linked above) and creator videos at the linked timestamps. EU status is information, not legal advice; see how we check.
MiniCPM5-1B is the first model in OpenBMB's MiniCPM5 series. It is a dense causal language model with about 1.08 billion parameters (about 680 million non-embedding), 24 layers, grouped-query attention (16 query / 2 KV heads) and a 131,072-token context window. It uses the standard LlamaForCausalLM architecture, so it loads in common tooling such as Transformers.
The model is aimed at local assistants, coding agents, tool-use workflows and reasoning on resource-constrained hardware such as laptops and phones. It supports a hybrid mode: a built-in <think> chat template can be toggled with enable_thinking, so one checkpoint serves as both a fast assistant and a deliberate reasoner. OpenBMB reports that it leads comparable open models (LFM2.5-1.2B-Thinking, Qwen3-0.6B and Qwen3.5-0.8B) mainly on tool use, code generation and difficult reasoning; these are vendor-reported results.
Weights are released under Apache-2.0 on Hugging Face and ModelScope. Variants include SFT-only and base checkpoints, GGUF for llama.cpp/Ollama/LM Studio, and a 4-bit MLX build for Apple Silicon. The card lists English and Chinese as supported languages. As a 1B model, it has limited world knowledge and capability compared with larger models.
Watch the moment: the exact second top creators show it. Videos load only when you press play, via youtube-nocookie.com.
Tiny 1B-parameter dense model, about 2 GB, that outperforms similarly sized models on knowledge, coding, math, reasoning and agentic benchmarks. Runs on laptops or phones.
Closest neighbours by meaning, not just by category.
Model · OpenBMB
Dense 2B-parameter open-weights language model from OpenBMB for on-device and edge deployment, Apache-2.0 licensed.
Model · OpenBMB
Small open-weights multimodal model from OpenBMB for image and video understanding on phones and edge devices.
Model
Compact 1.7B open-weights text LLM for on-device use, with adjustable thinking levels and English/Chinese support.
Model · Alibaba
Small 0.8B-parameter open-weights language model in Alibaba's Qwen 3.5 family, aimed at lightweight and on-device use.
Model · MiniMax
Open-weights native multimodal MoE model from MiniMax, ~428B parameters (~23B active) with 1M-token context.
Model · Google
Google DeepMind's family of open-weights models built from Gemini technology, from phone-sized to laptop-class variants.
