Issues / #520

#520 [2x RTX PRO 6000] Would this approach allow me to run full bf16 model?

closed · @lulinxuan · 2 comments · View on GitHub

Multi-GPUNVIDIA / CUDA

Description

As the title described, will this model allow me to use RAM and SSD offload to run the full bf16 model of qwen 3.8 flash next?

Related on strata.com

Editorial links to help you install, pick models, or read release notes — not part of the upstream thread.