MiniCPM5 2B is Openbmb's language model. A compact large language model optimized for efficient on-device inference at the 2B parameter scale.
| Benchmarks | |
|---|---|
| Intelligence Index | #257 |
| Coding Index | #171 |
| GPQA | #266 |
| HLE | #259 |
| Time to First Token | #297 |
| SciCode | #372 |
| LCR | #203 |
| Output TPS | #513 |
Capabilities
Input1/5
Text✓
Image·
Audio·
Video·
PDF·
Output1/5
Text✓
Image·
Audio·
Video·
Embedding·
Capabilities0/13
Reasoning·
Adaptive Reasoning·
Function Calling·
Parallel Function Calling·
Structured Outputs·
Native JSON Schema·
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching·
Assistant Prefill·
Cheapest Instances to Run It
Cloud GPU instances that can host MiniCPM5 2B, ranked by cheapest on-demand price. The model needs about 5 GB of GPU memory at FP16 precision (estimated from its parameter count), so treat the fit as guidance rather than a guarantee.
All clouds
FP16 (full precision)
US Dollar ($)
Instance | Cloud | GPU | VRAM | Price | Cheapest region | |
|---|---|---|---|---|---|---|
| Standard_NV4as_v4 |  Azure | AMD Radeon Instinct MI25 | 16 GB | $0.233/hr | ||
| g5g.xlarge |  AWS | T4g | 16 GB | $0.420/hr | ||
| Standard_NV8as_v4 | Azure | AMD Radeon Instinct MI25 | 16 GB | $0.466/hr | ||
Versions
| Version | Released | Context | Input / 1M | Output / 1M | Status |
|---|---|---|---|---|---|
| MiniCPM5 2B | — | — | — | — | Current |
| MiniCPM5 1B Non-Reasoning | — | — | — | — | Available |
| MiniCPM5 1B | — | — | — | — | Available |
| MiniCPM-V 4.6 1.3B | — | — | — | — | Available |
| MiniCPM-V 4.5 VL | — | 32K | — | — | Available |