ORBIS ELECTRIC
O|E
100 MW IT AI SCALE REFERENCE POINT
Staying Ahead of NVIDIA's
Next Chiller-less Generation
Next Chiller-less Generation
COOL•E™
How Cool-E™ Potentially Reallocates 8+ MW to IT / Rubin-Class
Rack Reallocation
Rubin: 102 racks
freed per 100MW, deployed on Rubin chips (4 branches active), vs. a projected Rubin-era competitor
GB200 Cool-E vs. Rubin Cool-E
Buying Rubin-ready hardware costs nothing if you only run GB200 chips today. Same current draw, plus better chiller margin as a bonus — you're just not using the 4th branch yet.
| Config | Branches | Flow | Approach | MCA |
|---|---|---|---|---|
| GB200 Cool-E | 2+1 | 476 GPM | 2.4K | 27A |
| Rubin Cool-E | 3+1 | 787 GPM | 2.4K | 49A |
| Rubin hardware, running GB200 only | 2 of 4 | 476 GPM | 1.1K ↓ | 27A |
Cool-E Rubin Spec
2.4K
Approach
42.6°C
Tci_max
787
GPM / 2MW CDU
3+1
Motors / branches
49A
MCA, DC-native / CDU
68A
MCA, AC-retrofit / CDU
How This Works
| Step | Logic | Result |
|---|---|---|
| 1. Same heat, tighter spread | Q = flow × ΔT. Same 2MW, but Rubin's ΔT is half GB200's (10K vs 20K) | Total flow: 476 → 787 GPM |
| 2. Split across a new motor | Cool-E adds a branch instead of pushing existing motors harder | Per-motor flow: 238 → 262.3 GPM (+10%) |
| 3. Current follows flow², per motor | 1.10² = 1.22 — a real physical relationship, not a guess | Per-motor current: +22% |
| 4. More motors, too | 2 active → 3 active | ×1.5 motor count |
| Total | 1.22 × 1.5 = 1.82 | MCA: 27A ‚Üí 49A (+82%) |