700B Parameter LLM on the VENTUNO Q!
Streaming the model from storage using an NVME SSD & Colibri enables cloud-sized models, even on your VENTUNO Q.
Devices & Components
1
Arduino®️ VENTUNO™ Q
1
1TB SSD (PCIe Gen4 NVMe 2230 M.2)
Software & Tools
Colibri GitHub
Project description
Code
Colibri Runtime
Comments
Only logged in users can leave comments