Running a 26B MoE model on an 8GB GPU
A practical note from a real homelab experiment: what mattered when running a 26B MoE model on an RTX 2070 SUPER with 8GB of VRAM.
Topic
Deployments, incidents, verification, and the work around the work.
A practical note from a real homelab experiment: what mattered when running a 26B MoE model on an RTX 2070 SUPER with 8GB of VRAM.
A small story about SportsReel, Padel Centenario, a wrong upload, and why useful automation needs verification.