Can I run MiniCPM5 2B on my own hardware?

Name: MiniCPM5 2B
Brand: huggingface

Yes — MiniCPM5 2B is an open-weight model you can run on a workstation or on-prem server you own. At Q4_K_M it needs roughly 1.9 GB of GPU memory, plus room for the context cache — it fits a single 8 GB card. Wide Area Intelligence routes requests to your own nodes first and fails over to the cloud only when they can't serve.

← model directory

huggingface

MiniCPM5 2B

hf/openbmb/MiniCPM5-2B-GGUF

↓ runs free on your own hardware⚙ tool calling

Open-weight model — runs free on your own GPU via the node runtime (GGUF). 180,593 downloads and 280 likes on Hugging Face (openbmb/MiniCPM5-2B-GGUF).

specs & pricing

Type: text
Provider: huggingface
Model ID: hf/openbmb/MiniCPM5-2B-GGUF
Capabilities: tools
Self-hostable: Yes — runs on your own GPU

Listed in the directory for discovery. textmodels aren't callable through the chat gateway yet — image and video models can run on your own nodes today.

Run it on your own hardware

Estimated GPU memory for MiniCPM5 2B (2.0B parameters), for the weights alone — add room for the context cache.

Q4_K_M: ~1.9 GBfits a 8 GB card
Q8_0: ~2.7 GBfits a 8 GB card
FP16 / BF16: ~4.5 GBfits a 8 GB card

Install the agent on the machine and it dials out to the gateway over a single WebSocket — no port forwarding or inbound firewall rules. Requests for this model go to your node first and fail over to the cloud only when it can't serve.

VRAM calculator →Which GPU do I need? →

/// initialize

Call MiniCPM5 2B through one OpenAI-compatible endpoint.

Serve it from hardware you own, with cloud failover when your nodes are busy or offline.

Run it on your own hardware

no credit card · 2 nodes free · openai-compatible

Frequently asked questions

Can I run MiniCPM5 2B on my own hardware?: Yes — MiniCPM5 2B is an open-weight model you can run on a workstation or on-prem server you own. At Q4_K_M it needs roughly 1.9 GB of GPU memory, plus room for the context cache — it fits a single 8 GB card. Wide Area Intelligence routes requests to your own nodes first and fails over to the cloud only when they can't serve.

More from huggingface

← browse all models