← Back to Models
MiniCPM-V
A series of multimodal LLMs (MLLMs) designed for vision-language understanding.
minicpm-v-2.0
2.8B parameters
Multimodal
Pull this model
Use the following command with the HoML CLI:
homl pull minicpm-v:2.0Resource Requirements
| Quantization | Disk Space | GPU Memory |
|---|---|---|
| BF16 | 5.6 GB | 5.6 GB |
minicpm-llama3-v-2.5
8B parameters
Multimodal
Pull this model
Use the following command with the HoML CLI:
homl pull minicpm-v:2.5Resource Requirements
| Quantization | Disk Space | GPU Memory |
|---|---|---|
| BF16 | 16 GB | 16 GB |
minicpm-v-2.6
8B parameters
Multimodal
Pull this model
Use the following command with the HoML CLI:
homl pull minicpm-v:2.6Resource Requirements
| Quantization | Disk Space | GPU Memory |
|---|---|---|
| BF16 | 16 GB | 16 GB |