AIXX Pedia › Model Comparison › B300 × GB300 NVL72
| Parameter | NVIDIA B300 · Blackwell Ultra | NVIDIA GB300 NVL72 · Blackwell Ultra Super Node Rack |
|---|---|---|
| Architecture | Blackwell Ultra | Blackwell Ultra Super Node (rack-level) |
| Process | TSMC 4NP | — |
| Board Memory | 288GB HBM3e (2.3TB across eight GPUs) | 288GB HBM3e per GPU (20TB HBM3e per rack · per official page) |
| Memory Bandwidth | Approx. 8TB/s per card (nominal) | Up to 576TB/s per rack |
| GPU-to-GPU Interconnect | NVLink 5 · 1.8TB/s | NVLink 5 · 130TB/s per rack (1.8TB/s per GPU) + fully interconnected via 9× NVSwitch trays |
| Board Power (TBP/TGP) | 1100W per card (both air-cooled and liquid-cooled variants) | Rack power provisioned at 132kW configuration level (8× 33kW power shelves; NVIDIA reference architecture peaks at 142kW under full load) |
| Form Factor & Cooling | 8-GPU air-cooled (NVL8) · 16-GPU liquid-cooled (NVL16) · GB300 superchip series | Fully liquid-cooled rack (18× compute trays + 9× NVSwitch trays · in-rack CDU at 250kW class) |
| Launch / Delivery | Announced at GTC 2025-03 · Shipping from H2 2025 | Announced at GTC on 2025-03-18 · full-rack delivery by 16 partners from H2 2025 |
| China-market Timeline | In-stock circulation in mainland China since H2 2025 · Shortage persists | Not on the approved list for China (export-controlled item) · spot availability mainly via overseas and free-trade-zone channels (based on public reporting, not legal advice) |
| Mainland China Street Price Band | Approx. RMB 15–17M per unit (as of the entry's 2026-10 update); market listings on 10-07 at 10.72–15.02M (31 listings) | ¥40.41M–45.29M per rack (2026-10-08 hall real-time · 15 listings · full-rack asking price basis · overseas and free-trade-zone channel context) |
| Configuration | — | 72× Blackwell Ultra GPU + 36× Grace CPU (2,592× Arm Neoverse V2 cores) |
Specs are based on NVIDIA official public documentation and the two entry pages; price bands reflect actual on-sale listings in this library's marketplace and fluctuate with inventory—see the entry page "price band" for the latest. A dash in both columns means the entry does not yet include this parameter.
AIXX Index (0–100): estimated by this library using a weighted public-spec model—memory 40% + interconnect 30% + ecosystem 30%, weights adjusted by scenario. 90+ flagship · 75+ Excellent · 60+ usable · below 60 not applicable. The method is transparent and verifiable and does not constitute a performance promise; figures match the published figures on the two entry pages, so this page does not score separately.
| Scenario Index | B300 | GB300 NVL72 |
|---|---|---|
| LLM Inference | 94 | —Not rated |
| Model Training / Fine-tuning | 86 | —Not rated |
| Video Generation | 82 | —Not rated |
| Development / Workstation | 35 | —Not rated |
| Scientific Computing / HPC | 38 | —Not rated |
| Trillion-Parameter Training | —Not rated | 96 |
| Inference Factory (High-Concurrency MoE) | —Not rated | 94 |
| Cluster Starting Point (AI Factory) | —Not rated | 90 |
| Large Memory, Long Context / Multi-Replica Full-Scale LLMs | —Not rated | 92 |
| Light Retrofit of Legacy Data Rooms | —Not rated | 45 |
| Condition / Reliability / Value Retention (Experience Index) | Pending hands-on testing | Pending hands-on testing |
"—" = the machine's entry page has no rating for this scenario; this page does not fill it in. The Experience Index (condition/reliability/value retention) is pending hands-on testing—inspection batch data is being accumulated and will light up unit by unit as Inspection Reports are published.
After this comparison, return to the entry pages to verify details and the latest price bands: