MiniCPM-V 4.7 35B-A3B
MiniCPM-V 4.7 35B-A3B is a public OpenBMB vision-language checkpoint uploaded on October 6. Its official repository contains 16 downloadable BF16 weight shards totaling approximately 35.21B parameters, a hybrid linear/full-attention mixture-of-experts language configuration, and image/video processing metadata. The configuration permits 262,144 positions, but no model card or validated context specification was published in the inspected repository, so no supported context limit is asserted here. Text and visual inputs produce language output through the conditional-generation architecture. The license, training ancestry, evaluated capabilities, and benchmark results remain undisclosed at the audit time; a public weight upload does not supply missing usage rights.
Specifications
- Parameters
- 35.21B total; approximately 3B active tier
- Architecture
- Hybrid linear/full-attention vision-language Mixture-of-Experts Transformer
- License
- Undisclosed
- Type
- multimodal
- Modalities
- textimagevideo
Benchmark Scores
Advanced Specifications
- Model Family
- MiniCPM
- API Access
- Not Available
- Chat Interface
- Not Available
Capabilities & Limitations
- Capabilities
- vision-language generationimage inputvideo input
- Known Limitations
- No weight license or model card was present at audit timeArchitectural maximum context is not a validated operating limitTraining ancestry and benchmark performance are unverifiedUse requires compatible new model and processor implementations
- Notable Use Cases
- evaluation of a newly published vision-language checkpointmultimodal deployment research