MiniCPM4 models
4 MiniCPM4 models from OpenBMB on Hugging Face, from 434M to 8.2B parameters, published by OpenBMB in BF16, with contexts from 32K to 64K tokens. The smallest official model, MiniCPM4-0.5B, needs about 1.0 GB of VRAM at its published precision; the cheapest live fit is RTX 3070 at $0.088/hr.
Pick a size
One row per official MiniCPM4 size: the VRAM it needs at each precision, the cheapest GPU that holds it today, and the KV cache for a 32K-token context.
| Model | Parameters | Native VRAM | FP8 VRAM | INT4 VRAM | Live GPU fit (native) | Est. $/hr | KV cache at 32K |
|---|---|---|---|---|---|---|---|
| MiniCPM4-0.5B | 434M | 1.0 GB | 0.5 GB | 0.2 GB | RTX 3070 | $0.088/hr | 0.38 GB |
| MiniCPM4.1-8B | 8.2B | 18.3 GB | 9.1 GB | 4.6 GB | RTX A5000 | $0.176/hr | 1.0 GB |
VRAM is weights times a flat 1.2 overhead; the KV cache is a separate per-model figure at 16-bit, shown where the architecture is published. See the methodology.
Official models (4)
| Model | Parameters | Published as | VRAM needed | Live GPU fit | Est. $/hr |
|---|---|---|---|---|---|
| MiniCPM4-0.5B | 434M | BF16 | 1.0 GB | RTX 3070 | $0.088/hr |
| MiniCPM4-8B | 8.2B | BF16 | 18.3 GB | RTX A5000 | $0.176/hr |
| MiniCPM4-MCP | 8.2B | BF16 | 18.3 GB | RTX A5000 | $0.176/hr |
| MiniCPM4.1-8B | 8.2B | BF16 | 18.3 GB | RTX A5000 | $0.176/hr |
VRAM is for the precision the model is published in: the weights times a flat 1.2 overhead, with the KV cache not included. See the methodology. The fit shown is the lowest-priced single GPU type that holds the model at that precision, or the lowest-priced multi-GPU set (up to 8) when none does.