MiniCPM-V — local AI model by OpenBMB
Written by Jakub Rusinowski · Last updated
OpenBMB's pocket-sized multimodal line, backed by ModelBest and Tsinghua University, built around one goal: image and video understanding that actually runs on a phone. Version 4.5 is the 8B that beat much larger proprietary models on OpenCompass; version 4.6 is the 1.3B successor that cut visual-encoding FLOPs by more than half and ships on iOS, Android and HarmonyOS.
Variants
The smallest MiniCPM-V variant needs about 2 GB of VRAM at Q4_K_M — quantized weights plus framework overhead, before any KV cache.
| Model | VRAM at Q4 | VRAM | Context | Run it |
|---|---|---|---|---|
| MiniCPM-V 4.6 → 1.3B | ~1.6 GB | 262,144 | ollama run minicpm-v4.6 | |
| MiniCPM-V 4.5 → 8B | ~5.6 GB | 32,768 | ollama run minicpm-v4.5 |
Memory is quantized weights plus overhead at Q4_K_M, from the same engine as the GPU & VRAM checker.
How to run MiniCPM-V locally
Install Ollama, then pull the tag.
ollama run minicpm-v4.6Pick a size above for its own VRAM figure, speed estimate and install command.
Licence
Commercial use permitted. No usage restrictions beyond attribution.
Applies to: MiniCPM-V 4.6Weights are downloadable and commercial use is permitted, subject to the licence’s acceptable-use terms.
Applies to: MiniCPM-V 4.5Recommended GPU
The cheapest catalogued GPU that runs MiniCPM-V locally (min 2 GB VRAM) is the Intel Arc B570 (10 GB).
Can I run MiniCPM-V on my GPU?
- MiniCPM-V on AMD Radeon RX 9060 XT 8GB
- MiniCPM-V on Intel Arc B570
- MiniCPM-V on Intel Arc B580
- MiniCPM-V on NVIDIA GeForce RTX 3060 (12GB)
- MiniCPM-V on NVIDIA GeForce RTX 3070
- MiniCPM-V on NVIDIA GeForce RTX 3070 Ti
- MiniCPM-V on NVIDIA GeForce RTX 3080 (10GB)
- MiniCPM-V on NVIDIA GeForce RTX 4060
- MiniCPM-V on NVIDIA GeForce RTX 4070
- MiniCPM-V on NVIDIA GeForce RTX 4070 Super
- MiniCPM-V on NVIDIA GeForce RTX 4070 Ti
- MiniCPM-V on NVIDIA GeForce RTX 5060
- MiniCPM-V on NVIDIA GeForce RTX 5060 Ti 8GB
- MiniCPM-V on NVIDIA GeForce RTX 5070
MiniCPM-V — frequently asked questions
How much VRAM does MiniCPM-V need?
MiniCPM-V needs about 2 GB VRAM at Q4_K_M quantization for its smallest variant. Variants: MiniCPM-V 4.6 (2 GB, Q4_K_M); MiniCPM-V 4.5 (6 GB, Q4_K_M). On Apple Silicon, unified memory counts toward this requirement.
Can I run MiniCPM-V on an RTX 4090 (24 GB)?
Yes — MiniCPM-V runs on an RTX 4090 (24 GB) and other 24 GB cards such as the RTX 3090. Smaller variants also fit comfortably on 8–16 GB GPUs at Q4_K_M.
What quantization should I use for MiniCPM-V?
Q4_K_M is the best balance of quality and VRAM for MiniCPM-V in most cases. Choose Q8_0 for near-lossless quality if you have spare VRAM, or smaller quants (Q3/Q2) only when memory is tight.
How do I run MiniCPM-V with Ollama?
Install Ollama, then run: ollama run minicpm-v4.6. This downloads MiniCPM-V and starts a local, OpenAI-compatible endpoint — no internet connection is needed after the initial download.