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.

ModelParametersNative VRAMFP8 VRAMINT4 VRAMLive GPU fit (native)Est. $/hrKV cache at 32K
MiniCPM4-0.5B434M1.0 GB0.5 GB0.2 GBRTX 3070$0.088/hr0.38 GB
MiniCPM4.1-8B8.2B18.3 GB9.1 GB4.6 GBRTX A5000$0.176/hr1.0 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)

ModelParametersPublished asVRAM neededLive GPU fitEst. $/hr
MiniCPM4-0.5B434MBF161.0 GBRTX 3070$0.088/hr
MiniCPM4-8B8.2BBF1618.3 GBRTX A5000$0.176/hr
MiniCPM4-MCP8.2BBF1618.3 GBRTX A5000$0.176/hr
MiniCPM4.1-8B8.2BBF1618.3 GBRTX 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.

More from OpenBMB

Start ComfyUI on a rented GPU.

© 2026 Aquanode. All rights reserved.

All trademarks, logos and brand names are the property of their respective owners.