20+ models
A Pocket-Sized MLLM for Ultra-Efficient Image and Video Understanding on Your Phone
A GPT-4o Level MLLM for Single Image, Multi Image and High-FPS Video Understanding on Your Phone
A series of multimodal LLMs (MLLMs) designed for vision-language understanding.
North Mini Code is Cohere's first model for developers — a 30B Mixture-of-Experts model with 3B active parameters, built for agentic software engineering.
MiniCPM-V 4.7 — the latest multimodal LLM in the MiniCPM-V series, in 1B and 35B-A3B (MoE) variants. Single-image, multi-image, and video understanding, with smooth on-device MoE inference.
MiniCPM-V4.7 1B (Abliterated/Uncensored) - excellent multimodal vision understanding, reasoning with a low 0.0122 KL divergence.
Uncensored/Abliterated MiniCPM5-2B with only 10/100 refusals. It achieves 2B-class SOTA, remains competitive with 4B models overall.
MiniCPM-V 4.6 vision model (1.3B): image understanding and OCR in about 1.6 GB. Image input works.
A 2B single-pass calibrated System 1 decision model built on MiniCPM5.
SOTA on-device LLMs, small yet powerful
highly efficient large language models (LLMs) designed explicitly for end-side devices
MiniCPM5-2B is a dense 2B Transformer for on-device deployment. It achieves 2B-class SOTA, remains competitive with 4B models overall, and excels in coding, math, long-context, tool use, and agentic tasks.
A decensored bilingual 1B mergeset model for roleplay and thinking tasks. Made by RACER IS OP.
A lightweight Ollama build of MiniCPM5-2B, the 2B-class open-source SOTA model from OpenBMB
Compact 2.5B model by OpenBMB — 2B-class open-source SOTA, built for on-device, local assistants, coding agents and tool-use workflows
A decensored bilingual (EN/ZH) 1B model built on MiniCPM5. Made by RACER IS OP.