Can I run Swift 1.5 Qwen3.8 27B GSQ RCO on my own hardware?

Name: Swift 1.5 Qwen3.8 27B GSQ RCO
Brand: huggingface

Yes — Swift 1.5 Qwen3.8 27B GSQ RCO is an open-weight model you can run on a workstation or on-prem server you own. At Q4_K_M it needs roughly 16.1 GB of GPU memory, plus room for the context cache — it fits a single 24 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

Swift 1.5 Qwen3.8 27B GSQ RCO

hf/ukisai/Swift-1.5-Qwen3.8-27B-GSQ-RCO-GGUF

↓ runs free on your own hardware⚙ tool calling

Open-weight model — runs free on your own GPU via the node runtime (GGUF). 620,314 downloads and 304 likes on Hugging Face (ukisai/Swift-1.5-Qwen3.8-27B-GSQ-RCO-GGUF).

specs & pricing

Type: text
Provider: huggingface
Model ID: hf/ukisai/Swift-1.5-Qwen3.8-27B-GSQ-RCO-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 Swift 1.5 Qwen3.8 27B GSQ RCO (27B parameters), for the weights alone — add room for the context cache.

Q4_K_M: ~16.1 GBfits a 24 GB card
Q8_0: ~27.4 GBfits a 32 GB card
FP16 / BF16: ~51.0 GBfits a 80 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 Swift 1.5 Qwen3.8 27B GSQ RCO 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 Swift 1.5 Qwen3.8 27B GSQ RCO on my own hardware?: Yes — Swift 1.5 Qwen3.8 27B GSQ RCO is an open-weight model you can run on a workstation or on-prem server you own. At Q4_K_M it needs roughly 16.1 GB of GPU memory, plus room for the context cache — it fits a single 24 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