MiniCPM-V 4.7 35B A3B
Active Parameters
35B
Context Length
262K
Modality
Text
Architecture
Mixture of Experts (MoE)
License
Apache 2.0
Release Date
7 Oct 2026
Knowledge Cutoff
-
API Pricing (per 1M)
Self-hosted only
System Requirements
VRAM requirements for different quantization methods and context sizes
1,024 tokens
Consumer
4x RTX 4090
24GB VRAM
Datacenter
1x NVIDIA A100
80GB VRAM
Apple Silicon
1x Apple M3 Max
128GB VRAM
262,144 tokens
Consumer
5x RTX 4090
24GB VRAM
Datacenter
2x NVIDIA A100
80GB VRAM
Apple Silicon
1x Apple M3 Max
128GB VRAM
Architecture Diagram
Evaluation Benchmarks
No evaluation benchmarks for MiniCPM-V 4.7 35B A3B available.
Rankings
Overall Rank
-
Coding Rank
-
About MiniCPM-V 4.7 35B A3B
MiniCPM-V 4.7 35B A3B is a mixture-of-experts multimodal foundation model featuring 3B active parameters per token. It delivers efficient high-resolution image and video comprehension with strong reasoning capabilities.
Technical Specifications
Attention
Attention Structure
Grouped-Query Attention
Attention Heads
16
Key-Value Heads
2
Attention Head Dimension
256
Position Embedding
ROPE
RoPE Theta
10,000,000
Sliding Window Attention
No
Sliding Window Size
-
Sliding Window Ratio
-
Linear Attention
Yes
Linear Attention Ratio
75.0%
Normalization
RMS Normalization
Activation Function
SwigLU
Dimensions
Auxiliary Parameters
-
Hidden Dimension Size
2,048
Number of Layers
40
FFN Intermediate Size (Dense)
-
Multi-Token Prediction Heads
1
Tokenizer
Vocabulary Size
248,144
Mixture of Experts
Total Expert Parameters
3.0B
Number of Experts
256
Active Experts
8
Shared Experts
-
FFN Intermediate Size (per Expert)
512
Dense Layers Before MoE
0
Resources
About MiniCPM
The MiniCPM model family developed by OpenBMB.