mirror of
https://github.com/ollama/ollama.git
synced 2026-04-30 01:38:56 -05:00
Replace binary low VRAM mode with tiered VRAM thresholds that set default context lengths for all models: - < 24 GiB VRAM: 4,096 context - 24-48 GiB VRAM: 32,768 context - >= 48 GiB VRAM: 262,144 context