MiniCPM5-2B
Parameters
2B
Context Length
131K
Modality
Text
Architecture
Dense
KV Cache Rate
42 KB/tok
License
Apache 2.0
Release Date
6 Sept 2026
Knowledge Cutoff
-
API Pricing (per 1M)
Self-hosted only
Hardware Sizing
Precision
Context
Workload Memory: 3.76 GB
INT4 · 8K context
Base Weights: 0.93 GB
KV Cache: 0.33 GB
Runtime & Graphs: 2.50 GB
Minimum Required Hardware
1x NVIDIA L4 24GB
3.8 / 21.6 GB usable
1x RTX 3060 12GB
3.8 / 10.8 GB usable
Apple M4 24GB
3.8 / 18.0 GB usable
Determine requirements for your specific workload:
Open in VRAM Calculator
Architecture Diagram
Evaluation Benchmarks
Rank
#187
| Benchmark | Score | Rank |
|---|---|---|
Agentic Index | 0.07 | 101 |
Coding Index | 0.14 | 140 |
Intelligence Index | 0.13 | 237 |
Rankings
Overall Rank
#187
Coding Rank
#143
About MiniCPM5-2B
MiniCPM5-2B is an edge-focused compact language model developed by OpenBMB and ModelBest. It delivers high-efficiency reasoning, instruction following, and multilingual text generation suitable for on-device deployment.
Technical Specifications
Attention
Attention Structure
Grouped-Query Attention
Attention Heads
16
Key-Value Heads
2
Attention Head Dimension
128
Position Embedding
ROPE
RoPE Theta
5,000,000
Normalization
RMS Normalization
Activation Function
SwigLU
Dimensions
Hidden Dimension Size
2,048
Number of Layers
42
FFN Intermediate Size (Dense)
6,144
Tokenizer
Vocabulary Size
130,560
Resources
About MiniCPM
The MiniCPM model family developed by OpenBMB.