{ "work_order": "WO-BUFFERED-FORWARD-01", "model": "Zamba2-7B-Instruct", "gpu": "RTX 3090 24GB", "results": [ { "config": "Dense BF16", "ppl": 4.8211, "tok_s": 1445.9, "vram_load_mb": 14032.0, "vram_peak_mb": 14686.0 }, { "config": "bnb 4-bit NF4", "ppl": 5.0664, "tok_s": 1579.4, "vram_load_mb": 5129.4, "vram_peak_mb": 5904.0 }, { "config": "HXQ 12-bit packed (buffered)", "ppl": 5.0153, "tok_s": 1763.7, "vram_load_mb": 5657.2, "vram_warmup_mb": 5864.6, "vram_peak_mb": 6510.7 }, { "config": "HXQ 12-bit packed (fused)", "ppl": 5.0228, "tok_s": 283.5, "vram_load_mb": 6079.5, "vram_peak_mb": 7108.9 } ], "cost": { "wall_time_s": -0.0, "hostname": "8552b21e-f647-40e8-ab36-30dc6fb62665", "timestamp": "2026-04-02T14:31:44" } }