MiniCPM V 4.7 35B A3B FP8

Name: MiniCPM V 4.7 35B A3B FP8
Author: OpenBMB

by OpenBMBMiniCPM

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

Released October 2026context N/A

A compact multimodal model that punches above its weight by using sparse activation — only 3B parameters fire at a time despite having 35B total, keeping inference costs low. It handles both text and image inputs, making it capable of visual understanding tasks without requiring the compute of a full dense model. The FP8 quantization further trims memory requirements, though this can introduce minor precision trade-offs compared to higher-precision variants.

Capabilities

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

Multimodal

Strong

Instruction Following

MiniCPM V 4.7 35B A3B FP8

by OpenBMBMiniCPM

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

Released October 2026context N/A

A compact multimodal model that punches above its weight by using sparse activation — only 3B parameters fire at a time despite having 35B total, keeping inference costs low. It handles both text and image inputs, making it capable of visual understanding tasks without requiring the compute of a full dense model. The FP8 quantization further trims memory requirements, though this can introduce minor precision trade-offs compared to higher-precision variants.

Capabilities

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

Multimodal

Strong

Instruction Following

Glossary

Dense ModelA neural network where all parameters are active for every input, in contrast to sparse architectures like mixture-of-experts that selectively activate different parts.FP8 QuantizationA compression technique that reduces model size by representing weights using 8-bit floating-point numbers instead of higher precision, making it faster and more memory-efficient.InferenceThe process of running a trained model to generate predictions or outputs from new inputs.MultimodalA model that can process and understand multiple types of input, such as both text and images.Multimodal ModelAn AI model that can process and understand multiple types of input data, such as video, images, and text together.ParametersThe learned numerical values in a model — more parameters generally means more capacity but higher compute cost.PrecisionThe level of numerical detail a model uses to represent its internal values; higher precision means more accurate calculations but requires more memory.QuantizationReducing a model's numerical precision (e.g., from 16-bit to 4-bit) to shrink memory usage and speed up inference.Sparse ActivationA technique where only a subset of a model's parameters are used for each input, reducing computational cost while maintaining performance.Visual UnderstandingThe ability of an AI model to interpret and analyze images, including identifying objects, reading text, and answering questions about visual content.

MiniCPM V 4.7 35B A3B FP8

Capabilities

MiniCPM V 4.7 35B A3B FP8

Capabilities

Use Case Fit

Similar Models

Glossary