[ { "label": "medium-slot1-priority2-draft-cuda1", "model": "pure", "ctx": 160000, "single": false, "split": "80,20", "ubatch": 128, "parallel": 1, "draft_max": 7, "draft_kv": "q4_0", "draft_device": "CUDA1", "quality": false, "prompts": [ 4096 ], "minimum_headroom_mib": 512 } ]