Inference at the edge without a building. I200C20 packs 200 kW of immersion capacity — 4× A32 tanks at up to 50 kW each — into a 20 ft factory-tested compute bay. Connect power, water, and network; earn in 75–90 days on repeat orders. 边缘推理，无需大楼。I200C20 将 200 kW 浸没容量 — 4 个 A32 液舱、每舱最高 50 kW — 装入 20 英尺工厂测试计算舱。接入电、水、网；复购订单可在 75–90 天内创收。
You've seen the business case — modular blocks, fast monetization, inference-first economics. I200C20 is the edge Immersion Computing Unit: a 20-ft container holding 4× A32 single-phase immersion tanks (up to 50 kW each · 200 kW IT). Servers sit fully submerged in dielectric fluid; dual redundant CDUs per tank carry heat to a warm-water loop. The compute bay is factory-integrated — on site you connect power, water, and network. 商业逻辑你已经看过——模块化区块、快速变现、以推理为先的经济模型。 I200C20 是边缘浸没计算单元：一台 20 英尺集装箱，内置 4 个 A32 单相浸没液舱（每舱最高 50 kW · 合计 200 kW IT）。 服务器完全浸没于绝缘冷却液；每舱双路冗余 CDU 将热量送入温水回路。 计算舱在工厂完成集成——现场只需接入电、水、网。
I200C20ST50IT Load vs. Facility Load. 200 kW is what the servers draw. Total facility load is ~440–500 kW once cooling and auxiliaries are added — the gap is set by PUE, which depends on your site's climate. *Sites whose historical peak dry-bulb stays ≤ 24 °C run on pure dry coolers (free cooling, lowest PUE); hotter sites add a hybrid chiller. Always confirm which figure an "X MW" requirement refers to. IT 负荷与设施总负荷。200 kW 指服务器实际用电。计入冷却与辅助系统后， 设施总负荷约为 440–500 kW——差值由 PUE 决定，而 PUE 取决于站点气候。 *历史极端干球温度 ≤ 24 °C 的站点可纯靠干冷器运行（自然冷却，PUE 最低）； 更热的站点需加装混合冷机。遇到「X MW」的需求时，务必确认指的是哪一个口径。
The whole server — GPUs, VRMs, NICs, DIMMs — is submerged in dielectric fluid. No cold plates to match to each SKU, no fans to fail, no hot spots. Up to 50 kW per 32RU tank, with both air-cooled servers retrofitted for immersion and immersion-ready designs supported. 整台服务器——GPU、VRM、网卡、内存——全部浸没在绝缘冷却液中。 无需为每个 SKU 匹配冷板，没有会坏的风扇，也没有热点。 每个 32RU 液舱最高 50 kW，既支持风冷服务器改造浸没，也支持原生浸没设计。
Oil enters the tank at ≤ 35 °C and leaves at ≈ 43 °C; the facility loop runs at 32/37 °C. Where the historical peak dry-bulb stays ≤ 24 °C, dry coolers alone reject all heat — no compressors, PUE as low as ≈ 1.05. Hotter sites add a hybrid chiller that trims only the peaks. 冷却油以 ≤ 35 °C 进舱、约 43 °C 出舱；设施侧回路运行在 32/37 °C。 当站点历史极端干球温度 ≤ 24 °C 时，仅靠干冷器即可排走全部热量—— 无需压缩机，PUE 可低至约 1.05。更热的站点加装混合冷机，仅在峰值时补冷。
Each A32 tank carries dual CDUs in full 2N — two pumps, plate heat exchanger, and filtration per CDU, hot-swappable in minutes without draining the tank. A single pump or CDU failure never stops the servers. 每个 A32 液舱配备完全 2N 的双路 CDU——每路含两台泵、板式换热器 与过滤单元，无需排油即可在数分钟内热插拔更换。单台泵或单路 CDU 故障都不会让服务器停机。
Orbit the compute bay cutaway — four A32 immersion tanks and service access. Cooling bay is excluded from this model.环绕计算舱剖视 — 四个 A32 浸没液舱与检修通道。本模型不含冷却舱。
Reference USD packages for immersion blocks are listed on the 40/45 ft product pages and Docs.浸没模块的参考 USD 包见 40/45 英尺产品页与文档。
I200C20 is the smaller immersion block for edge and pilot sites: a 20 ft compute bay with 4× A32 tanks (200 kW IT) and no built-in UPS. The I400C40 / I400C45 pods keep the same tank technology at 8× A32 (400 kW) in 40/45 ft containers — a different SKU class. I200C20 是面向边缘与试点的小型浸没模块：20 英尺计算舱， 4× A32 液舱（200 kW IT），无内置 UPS。I400C40 / I400C45 在 40/45 英尺箱内 使用相同液舱技术但为 8× A32（400 kW）——属于不同 SKU 档位。
| I200C20 | I400C40 / I400C45 | |
|---|---|---|
| SKU IDSKU ID | I200C20ST50 |
I400C40ST50 · I400C45SUT50 |
| Container箱体 | 20-ft compute bay20 英尺计算舱 | 40-ft / 45-ft40 英尺 / 45 英尺 |
| IT CapacityIT 容量 | 200 kW200 kW | 400 kW400 kW |
| Tanks液舱 | 4× A32 · up to 50 kW/tank4× A32 · 最高 50 kW/罐 | 8× A32 · up to 50 kW/tank8× A32 · 最高 50 kW/罐 |
| UPS | Not included不含 | I400C40 external · I400C45 built-inI400C40 外置 · I400C45 内置 |
| Best for最适合 | Edge / pilot / smaller footprints边缘 / 试点 / 更小占地 | Full 400 kW inference pods完整 400 kW 推理舱 |
Redundancy model. Tanks are 2N on cooling internally; a single container has no internal IT redundancy. System-level N / N+1 / 2N is built by adding containers. 冗余模型。液舱内部冷却为 2N；单箱不设 IT 冗余。系统级 N / N+1 / 2N 通过增加集装箱数量实现。
The full engineering model is live and interactive — every number computed from the same physics engine our design team uses, from tank-level oil flow to container PUE. 完整工程模型可在线交互——从液舱级油流量到整箱 PUE， 每个数字都来自我们设计团队所用的同一套物理引擎。
Walk the 4-tank compute bay of I200C20 (cooling bay not in this model).查看 I200C20 的 4 舱计算舱布局（本模型不含冷却舱）。
Watch the oil and water loops move through the dual-CDU tank diagram.在双 CDU 液舱示意图中观察油路与水路的流动。
Oil flow per tank (≈ 11–12 m³/h), facility water, and the ΔT budget.单舱油流量（约 11–12 m³/h）、设施侧水量，以及 ΔT 预算。
Pick a PCIe server and a climate — get GPU count, binding constraint, and PUE band.选定 PCIe 服务器与气候条件，即可得到 GPU 数量、约束瓶颈与 PUE 区间。