Apps & Tools
MiniCPM5-2B
A SOTA 2B-class open-source model optimized for edge AI and local inference.
byAJ
Playable
MiniCPM5-2B media is blocked
Allow external media to connect to the provider and play this content.
Description
MiniCPM5-2B is a dense 3B-parameter model with a 128k context window that achieves state-of-the-art results on math and code benchmarks, notably scoring 86.5 on AIME 2025 and 94.6 on MATH-500. Optimized for llama.cpp, it supports multiple GGUF quantization tiers (4-bit to 16-bit) and can run at over 100 t/s on consumer hardware like the RTX 3060.
Descriptions, tags, and model credits may be AI-generated or inferred from public sources and can be incomplete or wrong. Learn more.