MiniCPM5 2B MLX

Name: MiniCPM5 2B MLX
Author: OpenBMB

by OpenBMB

Open WeightModel weights are publicly available — can be downloaded and self-hosted

Released September 2026131K context≈ 98,304 words

A compact text model that punches above its weight class given its 2B parameter count, offering a surprisingly long 131K token context window for a model this small. It handles text-in, text-out tasks with the efficiency you'd expect from a miniaturized architecture. The MLX format suggests it's optimized for Apple Silicon environments, making it a practical choice for on-device or local inference workflows.

Capabilities

Capability scores are AI-generated based on model documentation, benchmarks, and technical specifications. Learn more

Long Context

Strong

Instruction Following

MiniCPM5 2B MLX

by OpenBMB

Open WeightModel weights are publicly available — can be downloaded and self-hosted

Released September 2026131K context≈ 98,304 words

A compact text model that punches above its weight class given its 2B parameter count, offering a surprisingly long 131K token context window for a model this small. It handles text-in, text-out tasks with the efficiency you'd expect from a miniaturized architecture. The MLX format suggests it's optimized for Apple Silicon environments, making it a practical choice for on-device or local inference workflows.

Capabilities

Capability scores are AI-generated based on model documentation, benchmarks, and technical specifications. Learn more

Long Context

Strong

Instruction Following

Glossary

Apple SiliconApple's custom-designed processors (like M1, M2, M3) optimized for running machine learning models on Mac computers.ArchitectureThe underlying structural design of a neural network that defines how data flows through layers and components.Context WindowThe maximum number of tokens a model can process in a single conversation or prompt.InferenceThe process of running a trained model to generate predictions or outputs from new inputs.Local InferenceRunning an AI model directly on your own computer rather than sending data to a remote server, keeping data private and reducing latency.MLXA machine learning framework optimized for running models efficiently on Apple Silicon chips.MLX FormatA model format designed specifically for efficient inference on Apple Silicon devices, optimized for the MLX machine learning framework.On-DeviceA model designed to run directly on a user's device (phone, laptop, etc.) rather than requiring a remote server.Parameter CountThe total number of adjustable weights in a model; more parameters generally mean more capacity to learn, but also require more computing power.Text ModelA language model that processes and generates only text, without support for images, audio, or other media types.Text-In, Text-OutA model that accepts text as input and produces text as output, without support for images, audio, or other data types.TokenA small unit of text (a word, subword, or punctuation mark) that a language model breaks input into for processing.

Capabilities

Capabilities

Use Case Fit

Glossary