Can I run stable code 3b on my own hardware?

Name: stable code 3b
Brand: huggingface

Yes — stable code 3b is an open-weight model you can run on a workstation or on-prem server you own. At Q4_K_M it needs roughly 2.5 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

stable code 3b

hf/stabilityai/stable-code-3b

↓ runs free on your own hardware

Open-weight model — runs free on your own GPU via the node runtime (GGUF). 6,599 downloads and 669 likes on Hugging Face (stabilityai/stable-code-3b).

specs & pricing

Type: text
Provider: huggingface
Model ID: hf/stabilityai/stable-code-3b
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 stable code 3b (3.0B parameters), for the weights alone — add room for the context cache.

Q4_K_M: ~2.5 GBfits a 8 GB card
Q8_0: ~3.7 GBfits a 8 GB card
FP16 / BF16: ~6.3 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 stable code 3b 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 stable code 3b on my own hardware?: Yes — stable code 3b is an open-weight model you can run on a workstation or on-prem server you own. At Q4_K_M it needs roughly 2.5 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