{"id":18843,"date":"2026-09-16T20:13:13","date_gmt":"2026-09-16T13:13:13","guid":{"rendered":"https:\/\/droneth.or.th\/product\/supermicro-nvidia-gb300-nvl72\/"},"modified":"2026-09-16T20:13:13","modified_gmt":"2026-09-16T13:13:13","slug":"supermicro-nvidia-gb300-nvl72","status":"publish","type":"product","link":"https:\/\/droneth.or.th\/en\/product\/supermicro-nvidia-gb300-nvl72\/","title":{"rendered":"Supermicro NVIDIA GB300 NVL72"},"content":{"rendered":"<p><strong>Supermicro NVIDIA GB300 NVL72<\/strong> \u0e40\u0e1b\u0e47\u0e19 \u0e23\u0e30\u0e1a\u0e1a AI \u0e23\u0e30\u0e14\u0e31\u0e1a Data Center \u0e08\u0e32\u0e01 <strong>Supermicro<\/strong> \u0e40\u0e2b\u0e21\u0e32\u0e30\u0e2a\u0e33\u0e2b\u0e23\u0e31\u0e1a\u0e07\u0e32\u0e19 large-model training, HPC, AI factory, data-center inference \u0e23\u0e2d\u0e07\u0e23\u0e31\u0e1a\u0e01\u0e32\u0e23\u0e43\u0e0a\u0e49\u0e07\u0e32\u0e19\u0e23\u0e30\u0e14\u0e31\u0e1a\u0e2d\u0e07\u0e04\u0e4c\u0e01\u0e23 \u0e28\u0e39\u0e19\u0e22\u0e4c\u0e02\u0e49\u0e2d\u0e21\u0e39\u0e25 \u0e41\u0e25\u0e30\u0e07\u0e32\u0e19\u0e27\u0e34\u0e08\u0e31\u0e22\u0e14\u0e49\u0e32\u0e19 AI\/HPC<\/p>\n<p><strong>\u0e01\u0e32\u0e23\u0e43\u0e0a\u0e49\u0e07\u0e32\u0e19\u0e17\u0e35\u0e48\u0e40\u0e2b\u0e21\u0e32\u0e30\u0e2a\u0e21<\/strong><\/p>\n<ul>\n<li>large-model training<\/li>\n<li>HPC<\/li>\n<li>AI factory<\/li>\n<li>data-center inference<\/li>\n<\/ul>\n<p><strong>\u0e02\u0e49\u0e2d\u0e21\u0e39\u0e25\u0e17\u0e32\u0e07\u0e40\u0e17\u0e04\u0e19\u0e34\u0e04 (Product Specifications)<\/strong><\/p>\n<table style=\"width:100%\">\n<thead>\n<tr>\n<td><strong>section<\/strong><\/td>\n<td><strong>\u0e23\u0e32\u0e22\u0e25\u0e30\u0e40\u0e2d\u0e35\u0e22\u0e14\u0e2a\u0e40\u0e1b\u0e04<\/strong><\/td>\n<\/tr>\n<\/thead>\n<tbody>\n<tr>\n<td><strong>Model<\/strong><\/td>\n<td>Supermicro NVIDIA GB300 NVL72<\/td>\n<\/tr>\n<tr>\n<td><strong>\u0e23\u0e2b\u0e31\u0e2a\u0e2a\u0e34\u0e19\u0e04\u0e49\u0e32<\/strong><\/td>\n<td>SRS-GB300-NVL72<\/td>\n<\/tr>\n<tr>\n<td><strong>\u0e1b\u0e23\u0e30\u0e40\u0e20\u0e17\u0e23\u0e30\u0e1a\u0e1a<\/strong><\/td>\n<td>Rack-Scale AI Supercomputer<\/td>\n<\/tr>\n<tr>\n<td><strong>\u0e02\u0e19\u0e32\u0e14\u0e41\u0e23\u0e47\u0e04<\/strong><\/td>\n<td>48U<\/td>\n<\/tr>\n<tr>\n<td><strong>GPU<\/strong><\/td>\n<td>NVIDIA B300 (Blackwell Ultra) \u0e08\u0e4d\u0e32\u0e19\u0e27\u0e19 72 \u0e15\u0e31\u0e27<\/td>\n<\/tr>\n<tr>\n<td><strong>CPU<\/strong><\/td>\n<td>NVIDIA Grace CPU \u0e08\u0e4d\u0e32\u0e19\u0e27\u0e19 36 \u0e15\u0e31\u0e27<\/td>\n<\/tr>\n<tr>\n<td><strong>\u0e08\u0e4d\u0e32\u0e19\u0e27\u0e19 CPU Core \u0e23\u0e27\u0e21<\/strong><\/td>\n<td>2,592 Arm Neoverse V2 Cores<\/td>\n<\/tr>\n<tr>\n<td><strong>GPU Memory<\/strong><\/td>\n<td>\u0e2a\u0e39\u0e07\u0e2a\u0e38\u0e14 21TB HBM3e<\/td>\n<\/tr>\n<tr>\n<td><strong>Memory \u0e15\u0e48\u0e2d GPU<\/strong><\/td>\n<td>288GB HBM3e<\/td>\n<\/tr>\n<tr>\n<td><strong>System Memory<\/strong><\/td>\n<td>\u0e2a\u0e39\u0e07\u0e2a\u0e38\u0e14 17TB LPDDR5X<\/td>\n<\/tr>\n<tr>\n<td><strong>Fast Memory \u0e23\u0e27\u0e21<\/strong><\/td>\n<td>37TB<\/td>\n<\/tr>\n<tr>\n<td><strong>NVLink Bandwidth<\/strong><\/td>\n<td>130TB\/s<\/td>\n<\/tr>\n<tr>\n<td><strong>Storage Bays<\/strong><\/td>\n<td>\u0e2a\u0e39\u0e07\u0e2a\u0e38\u0e14 144 x E1.S PCIe Gen5<\/td>\n<\/tr>\n<tr>\n<td><strong>Compute Nodes<\/strong><\/td>\n<td>18 x 1U ARS-121GL-NB3<\/td>\n<\/tr>\n<tr>\n<td><strong>NVLink Switches<\/strong><\/td>\n<td>9 \u0e0a\u0e38\u0e14<\/td>\n<\/tr>\n<tr>\n<td><strong>Compute Fabric<\/strong><\/td>\n<td>NVIDIA Quantum-X800 InfiniBand \u0e2b\u0e23\u0e37\u0e2d Spectrum-X Ethernet<\/td>\n<\/tr>\n<tr>\n<td><strong>Network Speed<\/strong><\/td>\n<td>\u0e2a\u0e39\u0e07\u0e2a\u0e38\u0e14 800Gb\/s<\/td>\n<\/tr>\n<tr>\n<td><strong>In-Band Management<\/strong><\/td>\n<td>\u0e2a\u0e39\u0e07\u0e2a\u0e38\u0e14 200Gb\/s \u0e1c\u0e48\u0e32\u0e19 BlueField-3 DPU<\/td>\n<\/tr>\n<tr>\n<td><strong>Out-of-Band Management<\/strong><\/td>\n<td>1GbE \/ 10GbE<\/td>\n<\/tr>\n<tr>\n<td><strong>Power System<\/strong><\/td>\n<td>8 x 33kW Power Shelves<\/td>\n<\/tr>\n<tr>\n<td><strong>\u0e01\u0e4d\u0e32\u0e25\u0e31\u0e07\u0e44\u0e1f\u0e23\u0e27\u0e21<\/strong><\/td>\n<td>132kW<\/td>\n<\/tr>\n<tr>\n<td><strong>Cooling<\/strong><\/td>\n<td>Direct Liquid Cooling<\/td>\n<\/tr>\n<tr>\n<td><strong>In-Rack CDU<\/strong><\/td>\n<td>\u0e23\u0e2d\u0e07\u0e23\u0e31\u0e1a\u0e2a\u0e39\u0e07\u0e2a\u0e38\u0e14 250kW<\/td>\n<\/tr>\n<tr>\n<td><strong>\u0e04\u0e27\u0e32\u0e21\u0e01\u0e27\u0e49\u0e32\u0e07<\/strong><\/td>\n<td>600 \u0e21\u0e21.<\/td>\n<\/tr>\n<tr>\n<td><strong>\u0e04\u0e27\u0e32\u0e21\u0e25\u0e36\u0e01<\/strong><\/td>\n<td>1,068 \u0e21\u0e21.<\/td>\n<\/tr>\n<tr>\n<td><strong>Altitude<\/strong><\/td>\n<td>2,236 \u0e21\u0e21.<\/td>\n<\/tr>\n<tr>\n<td><strong>FP4 Tensor Core Performance<\/strong><\/td>\n<td>1,440 PFLOPS<\/td>\n<\/tr>\n<tr>\n<td><strong>FP8 \/ FP6 Tensor Core Performance<\/strong><\/td>\n<td>720 PFLOPS<\/td>\n<\/tr>\n<tr>\n<td><strong>FP16 \/ BF16 Tensor Core Performance<\/strong><\/td>\n<td>360 PFLOPS<\/td>\n<\/tr>\n<tr>\n<td><strong>TF32 Tensor Core Performance<\/strong><\/td>\n<td>180 PFLOPS<\/td>\n<\/tr>\n<tr>\n<td><strong>FP32 Performance<\/strong><\/td>\n<td>6 PFLOPS<\/td>\n<\/tr>\n<tr>\n<td><strong>FP64 Performance<\/strong><\/td>\n<td>100 TFLOPS<\/td>\n<\/tr>\n<tr>\n<td><strong>AI Workloads<\/strong><\/td>\n<td>AI Training, AI Inference, AI Reasoning, HPC<\/td>\n<\/tr>\n<tr>\n<td><strong>Technical detail<\/strong><\/td>\n<td>\u0e23\u0e30\u0e1a\u0e1a AI Supercomputer \u0e41\u0e1a\u0e1a Rack-Scale \u0e02\u0e19\u0e32\u0e14 48U<\/td>\n<\/tr>\n<tr>\n<td><strong>Technical detail<\/strong><\/td>\n<td>\u0e43\u0e0a\u0e49 NVIDIA B300 GPU \u0e08\u0e4d\u0e32\u0e19\u0e27\u0e19 72 \u0e15\u0e31\u0e27<\/td>\n<\/tr>\n<tr>\n<td><strong>Technical detail<\/strong><\/td>\n<td>\u0e43\u0e0a\u0e49 NVIDIA Grace CPU \u0e08\u0e4d\u0e32\u0e19\u0e27\u0e19 36 \u0e15\u0e31\u0e27<\/td>\n<\/tr>\n<tr>\n<td><strong>Technical detail<\/strong><\/td>\n<td>\u0e40\u0e0a\u0e37\u0e48\u0e2d\u0e21\u0e15\u0e48\u0e2d GPU \u0e1c\u0e48\u0e32\u0e19 NVLink \u0e04\u0e27\u0e32\u0e21\u0e40\u0e23\u0e47\u0e27 130TB\/s<\/td>\n<\/tr>\n<tr>\n<td><strong>Technical detail<\/strong><\/td>\n<td>\u0e23\u0e30\u0e1a\u0e1a\u0e23\u0e30\u0e1a\u0e32\u0e22\u0e04\u0e27\u0e32\u0e21\u0e23\u0e49\u0e2d\u0e19\u0e41\u0e1a\u0e1a Direct Liquid Cooling<\/td>\n<\/tr>\n<tr>\n<td><strong>Technical detail<\/strong><\/td>\n<td>Supermicro NVIDIA GB300 NVL72 \u0e23\u0e38\u0e48\u0e19 SRS-GB300-NVL72 \u0e40\u0e1b\u0e47\u0e19\u0e23\u0e30\u0e1a\u0e1a AI Supercomputer \u0e23\u0e30\u0e14\u0e31\u0e1a Rack-Scale \u0e17\u0e35\u0e48\u0e2d\u0e2d\u0e01\u0e41\u0e1a\u0e1a\u0e21\u0e32\u0e2a\u0e4d\u0e32\u0e2b\u0e23\u0e31\u0e1a\u0e07\u0e32\u0e19\u0e1b\u0e31\u0e0d\u0e0d\u0e32\u0e1b\u0e23\u0e30\u0e14\u0e34\u0e29\u0e10\u0e4c\u0e02\u0e19\u0e32\u0e14\u0e43\u0e2b\u0e0d\u0e48 \u0e01\u0e32\u0e23\u0e1d\u0e36\u0e01\u0e2a\u0e2d\u0e19\u0e42\u0e21\u0e40\u0e14\u0e25 (AI Training) \u0e01\u0e32\u0e23\u0e1b\u0e23\u0e30\u0e21\u0e27\u0e25\u0e1c\u0e25 AI Inference \u0e41\u0e25\u0e30 AI Reasoning \u0e42\u0e14\u0e22\u0e43\u0e0a\u0e49\u0e2a\u0e16\u0e32\u0e1b\u0e31\u0e15\u0e22\u0e01\u0e23\u0e23\u0e21 NVIDIA Grace Blackwell Ultra \u0e23\u0e38\u0e48\u0e19\u0e25\u0e48\u0e32\u0e2a\u0e38\u0e14 \u0e23\u0e30\u0e1a\u0e1a\u0e17\u0e31\u0e49\u0e07\u0e2b\u0e21\u0e14\u0e16\u0e39\u0e01\u0e23\u0e27\u0e21\u0e2d\u0e22\u0e39\u0e48\u0e20\u0e32\u0e22\u0e43\u0e19\u0e41\u0e23\u0e47\u0e04\u0e02\u0e19\u0e32\u0e14 48U \u0e40\u0e1e\u0e35\u0e22\u0e07\u0e41\u0e23\u0e47\u0e04\u0e40\u0e14\u0e35\u0e22\u0e27 \u0e1b\u0e23\u0e30\u0e01\u0e2d\u0e1a\u0e14\u0e49\u0e27\u0e22 NVIDIA B300 GPU \u0e08\u0e4d\u0e32\u0e19\u0e27\u0e19 72 \u0e15\u0e31\u0e27 \u0e41\u0e25\u0e30 NVIDIA Grace CPU \u0e08\u0e4d\u0e32\u0e19\u0e27\u0e19 36 \u0e15\u0e31\u0e27 \u0e40\u0e0a\u0e37\u0e48\u0e2d\u0e21\u0e15\u0e48\u0e2d\u0e01\u0e31\u0e19\u0e1c\u0e48\u0e32\u0e19\u0e40\u0e17\u0e04\u0e42\u0e19\u0e42\u0e25\u0e22\u0e35 NVLink \u0e23\u0e38\u0e48\u0e19\u0e17\u0e35\u0e48 5 \u0e41\u0e25\u0e30 NVLink Switch Fabric \u0e17\u0e4d\u0e32\u0e43\u0e2b\u0e49 GPU \u0e17\u0e31\u0e49\u0e07\u0e2b\u0e21\u0e14\u0e2a\u0e32\u0e21\u0e32\u0e23\u0e16\u0e17\u0e4d\u0e32\u0e07\u0e32\u0e19\u0e23\u0e48\u0e27\u0e21\u0e01\u0e31\u0e19\u0e40\u0e2a\u0e21\u0e37\u0e2d\u0e19\u0e40\u0e1b\u0e47\u0e19\u0e23\u0e30\u0e1a\u0e1a\u0e40\u0e14\u0e35\u0e22\u0e27\u0e02\u0e19\u0e32\u0e14\u0e43\u0e2b\u0e0d\u0e48\u0e44\u0e14\u0e49\u0e2d\u0e22\u0e48\u0e32\u0e07\u0e21\u0e35\u0e1b\u0e23\u0e30\u0e2a\u0e34\u0e17\u0e18\u0e34\u0e20\u0e32\u0e1e\u0e2a\u0e39\u0e07\u0e2a\u0e38\u0e14<\/td>\n<\/tr>\n<tr>\n<td><strong>Technical detail<\/strong><\/td>\n<td>\u0e23\u0e30\u0e1a\u0e1a\u0e23\u0e2d\u0e07\u0e23\u0e31\u0e1a\u0e2b\u0e19\u0e48\u0e27\u0e22\u0e04\u0e27\u0e32\u0e21\u0e08\u0e4d\u0e32 HBM3e \u0e23\u0e27\u0e21\u0e2a\u0e39\u0e07\u0e2a\u0e38\u0e14 21TB \u0e1a\u0e19\u0e1d\u0e31\u0e48\u0e07 GPU \u0e41\u0e25\u0e30\u0e2b\u0e19\u0e48\u0e27\u0e22\u0e04\u0e27\u0e32\u0e21\u0e08\u0e4d\u0e32 LPDDR5X \u0e23\u0e27\u0e21\u0e2a\u0e39\u0e07\u0e2a\u0e38\u0e14 17TB \u0e1a\u0e19\u0e1d\u0e31\u0e48\u0e07 CPU \u0e42\u0e14\u0e22\u0e41\u0e15\u0e48\u0e25\u0e30 GPU \u0e21\u0e35\u0e2b\u0e19\u0e48\u0e27\u0e22\u0e04\u0e27\u0e32\u0e21\u0e08\u0e4d\u0e32 HBM3e \u0e02\u0e19\u0e32\u0e14 288GB \u0e0b\u0e36\u0e48\u0e07\u0e0a\u0e48\u0e27\u0e22\u0e23\u0e2d\u0e07\u0e23\u0e31\u0e1a\u0e42\u0e21\u0e40\u0e14\u0e25 AI \u0e02\u0e19\u0e32\u0e14\u0e43\u0e2b\u0e0d\u0e48\u0e41\u0e25\u0e30\u0e07\u0e32\u0e19\u0e1b\u0e23\u0e30\u0e21\u0e27\u0e25\u0e1c\u0e25\u0e17\u0e35\u0e48\u0e15\u0e49\u0e2d\u0e07\u0e43\u0e0a\u0e49\u0e02\u0e49\u0e2d\u0e21\u0e39\u0e25\u0e08\u0e4d\u0e32\u0e19\u0e27\u0e19\u0e21\u0e2b\u0e32\u0e28\u0e32\u0e25\u0e44\u0e14\u0e49\u0e2d\u0e22\u0e48\u0e32\u0e07\u0e21\u0e35\u0e1b\u0e23\u0e30\u0e2a\u0e34\u0e17\u0e18\u0e34\u0e20\u0e32\u0e1e<\/td>\n<\/tr>\n<tr>\n<td><strong>Technical detail<\/strong><\/td>\n<td>\u0e20\u0e32\u0e22\u0e43\u0e19\u0e41\u0e23\u0e47\u0e04\u0e1b\u0e23\u0e30\u0e01\u0e2d\u0e1a\u0e14\u0e49\u0e27\u0e22 Compute Node \u0e08\u0e4d\u0e32\u0e19\u0e27\u0e19 18 \u0e0a\u0e38\u0e14 \u0e41\u0e25\u0e30 NVLink Switch \u0e08\u0e4d\u0e32\u0e19\u0e27\u0e19 9 \u0e0a\u0e38\u0e14 \u0e0b\u0e36\u0e48\u0e07\u0e2a\u0e23\u0e49\u0e32\u0e07\u0e41\u0e1a\u0e19\u0e14\u0e4c\u0e27\u0e34\u0e14\u0e17\u0e4c\u0e01\u0e32\u0e23\u0e40\u0e0a\u0e37\u0e48\u0e2d\u0e21\u0e15\u0e48\u0e2d\u0e23\u0e30\u0e2b\u0e27\u0e48\u0e32\u0e07 GPU \u0e2a\u0e39\u0e07\u0e16\u0e36\u0e07 130TB\/s \u0e1e\u0e23\u0e49\u0e2d\u0e21\u0e23\u0e2d\u0e07\u0e23\u0e31\u0e1a\u0e23\u0e30\u0e1a\u0e1a\u0e40\u0e04\u0e23\u0e37\u0e2d\u0e02\u0e48\u0e32\u0e22\u0e04\u0e27\u0e32\u0e21\u0e40\u0e23\u0e47\u0e27\u0e2a\u0e39\u0e07 NVIDIA Quantum-X800 InfiniBand \u0e2b\u0e23\u0e37\u0e2d NVIDIA Spectrum-X Ethernet \u0e1c\u0e48\u0e32\u0e19 NVIDIA ConnectX-8 SuperNIC \u0e17\u0e35\u0e48\u0e21\u0e35\u0e04\u0e27\u0e32\u0e21\u0e40\u0e23\u0e47\u0e27\u0e2a\u0e39\u0e07\u0e2a\u0e38\u0e14 800Gb\/s \u0e2a\u0e4d\u0e32\u0e2b\u0e23\u0e31\u0e1a\u0e07\u0e32\u0e19 AI Cluster \u0e41\u0e25\u0e30 HPC \u0e23\u0e30\u0e14\u0e31\u0e1a\u0e2d\u0e07\u0e04\u0e4c\u0e01\u0e23\u0e02\u0e19\u0e32\u0e14\u0e43\u0e2b\u0e0d\u0e48<\/td>\n<\/tr>\n<tr>\n<td><strong>Technical detail<\/strong><\/td>\n<td>Supermicro \u0e44\u0e14\u0e49\u0e2d\u0e2d\u0e01\u0e41\u0e1a\u0e1a\u0e23\u0e30\u0e1a\u0e1a\u0e23\u0e30\u0e1a\u0e32\u0e22\u0e04\u0e27\u0e32\u0e21\u0e23\u0e49\u0e2d\u0e19\u0e41\u0e1a\u0e1a Direct Liquid Cooling (DLC) \u0e40\u0e15\u0e47\u0e21\u0e23\u0e39\u0e1b\u0e41\u0e1a\u0e1a \u0e1e\u0e23\u0e49\u0e2d\u0e21\u0e15\u0e34\u0e14\u0e15\u0e31\u0e49\u0e07 Cooling Distribution Unit (CDU) \u0e20\u0e32\u0e22\u0e43\u0e19\u0e41\u0e23\u0e47\u0e04 \u0e23\u0e2d\u0e07\u0e23\u0e31\u0e1a\u0e01\u0e4d\u0e32\u0e25\u0e31\u0e07\u0e23\u0e30\u0e1a\u0e32\u0e22\u0e04\u0e27\u0e32\u0e21\u0e23\u0e49\u0e2d\u0e19\u0e2a\u0e39\u0e07\u0e2a\u0e38\u0e14 250kW \u0e0a\u0e48\u0e27\u0e22\u0e40\u0e1e\u0e34\u0e48\u0e21\u0e1b\u0e23\u0e30\u0e2a\u0e34\u0e17\u0e18\u0e34\u0e20\u0e32\u0e1e\u0e01\u0e32\u0e23\u0e43\u0e0a\u0e49\u0e1e\u0e25\u0e31\u0e07\u0e07\u0e32\u0e19\u0e41\u0e25\u0e30\u0e23\u0e2d\u0e07\u0e23\u0e31\u0e1a\u0e42\u0e2b\u0e25\u0e14\u0e01\u0e32\u0e23\u0e17\u0e4d\u0e32\u0e07\u0e32\u0e19\u0e23\u0e30\u0e14\u0e31\u0e1a\u0e2a\u0e39\u0e07\u0e44\u0e14\u0e49\u0e2d\u0e22\u0e48\u0e32\u0e07\u0e15\u0e48\u0e2d\u0e40\u0e19\u0e37\u0e48\u0e2d\u0e07 \u0e42\u0e14\u0e22\u0e23\u0e30\u0e1a\u0e1a\u0e44\u0e1f\u0e1f\u0e49\u0e32\u0e20\u0e32\u0e22\u0e43\u0e19\u0e41\u0e23\u0e47\u0e04\u0e21\u0e35\u0e04\u0e27\u0e32\u0e21\u0e2a\u0e32\u0e21\u0e32\u0e23\u0e16\u0e08\u0e48\u0e32\u0e22\u0e1e\u0e25\u0e31\u0e07\u0e07\u0e32\u0e19\u0e23\u0e27\u0e21\u0e2a\u0e39\u0e07\u0e16\u0e36\u0e07 132kW \u0e1c\u0e48\u0e32\u0e19 Power Shelf \u0e08\u0e4d\u0e32\u0e19\u0e27\u0e19 8 \u0e0a\u0e38\u0e14<\/td>\n<\/tr>\n<tr>\n<td><strong>Technical detail<\/strong><\/td>\n<td>NVIDIA \u0e23\u0e30\u0e1a\u0e38\u0e27\u0e48\u0e32 GB300 NVL72 \u0e44\u0e14\u0e49\u0e23\u0e31\u0e1a\u0e01\u0e32\u0e23\u0e2d\u0e2d\u0e01\u0e41\u0e1a\u0e1a\u0e21\u0e32\u0e40\u0e1e\u0e37\u0e48\u0e2d\u0e23\u0e2d\u0e07\u0e23\u0e31\u0e1a\u0e22\u0e38\u0e04\u0e02\u0e2d\u0e07 AI Reasoning \u0e42\u0e14\u0e22\u0e21\u0e35\u0e1b\u0e23\u0e30\u0e2a\u0e34\u0e17\u0e18\u0e34\u0e20\u0e32\u0e1e FP4 Tensor Core \u0e2a\u0e39\u0e07\u0e16\u0e36\u0e07 1,440 PFLOPS \u0e41\u0e25\u0e30\u0e2a\u0e32\u0e21\u0e32\u0e23\u0e16\u0e40\u0e1e\u0e34\u0e48\u0e21\u0e1b\u0e23\u0e30\u0e2a\u0e34\u0e17\u0e18\u0e34\u0e20\u0e32\u0e1e AI Factory \u0e44\u0e14\u0e49\u0e2a\u0e39\u0e07\u0e2a\u0e38\u0e14\u0e16\u0e36\u0e07 50 \u0e40\u0e17\u0e48\u0e32\u0e40\u0e21\u0e37\u0e48\u0e2d\u0e40\u0e17\u0e35\u0e22\u0e1a\u0e01\u0e31\u0e1a\u0e41\u0e1e\u0e25\u0e15\u0e1f\u0e2d\u0e23\u0e4c\u0e21 NVIDIA Hopper \u0e43\u0e19\u0e1a\u0e32\u0e07\u0e23\u0e39\u0e1b\u0e41\u0e1a\u0e1a\u0e07\u0e32\u0e19 AI Inference \u0e41\u0e25\u0e30 AI Reasoning \u0e02\u0e19\u0e32\u0e14\u0e43\u0e2b\u0e0d\u0e48<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<p>\u0e2a\u0e19\u0e43\u0e08\u0e2a\u0e2d\u0e1a\u0e16\u0e32\u0e21\u0e23\u0e32\u0e04\u0e32 \u0e2a\u0e40\u0e1b\u0e04 \u0e2b\u0e23\u0e37\u0e2d\u0e02\u0e2d\u0e43\u0e1a\u0e40\u0e2a\u0e19\u0e2d\u0e23\u0e32\u0e04\u0e32 \u0e15\u0e34\u0e14\u0e15\u0e48\u0e2d\u0e44\u0e14\u0e49\u0e17\u0e35\u0e48 <strong>LINE: @metaxr<\/strong><\/p>","protected":false},"excerpt":{"rendered":"<p><strong>Supermicro NVIDIA GB300 NVL72<\/strong> \u0e40\u0e1b\u0e47\u0e19 \u0e23\u0e30\u0e1a\u0e1a AI \u0e23\u0e30\u0e14\u0e31\u0e1a Data Center \u0e08\u0e32\u0e01 <strong>Supermicro<\/strong> \u0e40\u0e2b\u0e21\u0e32\u0e30\u0e2a\u0e33\u0e2b\u0e23\u0e31\u0e1a\u0e07\u0e32\u0e19 large-model training, HPC, AI factory, data-center inference \u0e23\u0e2d\u0e07\u0e23\u0e31\u0e1a\u0e01\u0e32\u0e23\u0e43\u0e0a\u0e49\u0e07\u0e32\u0e19\u0e23\u0e30\u0e14\u0e31\u0e1a\u0e2d\u0e07\u0e04\u0e4c\u0e01\u0e23 \u0e28\u0e39\u0e19\u0e22\u0e4c\u0e02\u0e49\u0e2d\u0e21\u0e39\u0e25 \u0e41\u0e25\u0e30\u0e07\u0e32\u0e19\u0e27\u0e34\u0e08\u0e31\u0e22\u0e14\u0e49\u0e32\u0e19 AI\/HPC<\/p>\n<div style=\"width: 100%; text-align: center; padding: 24px 0;\"><a style=\"display: inline-block; background-color: #06c755; color: #ffffff; font-size: 16px; font-weight: bold; text-decoration: none; padding: 14px 32px; border-radius: 50px; box-shadow: 0 4px 12px rgba(6,199,85,0.4); white-space: nowrap;\" href=\"https:\/\/page.line.me\/682mqqmh?openQrModal=true\" target=\"_blank\" rel=\"noopener\">\u0e2a\u0e2d\u0e1a\u0e16\u0e32\u0e21\u0e23\u0e32\u0e04\u0e32 \/ \u0e2a\u0e31\u0e48\u0e07\u0e0b\u0e37\u0e49\u0e2d LINE: @metaxr<\/a><\/div>","protected":false},"featured_media":19183,"comment_status":"closed","ping_status":"closed","template":"","meta":{"_acf_changed":false,"site-sidebar-layout":"default","site-content-layout":"","ast-site-content-layout":"default","site-content-style":"default","site-sidebar-style":"default","ast-global-header-display":"","ast-banner-title-visibility":"","ast-main-header-display":"","ast-hfb-above-header-display":"","ast-hfb-below-header-display":"","ast-hfb-mobile-header-display":"","site-post-title":"","ast-breadcrumbs-content":"","ast-featured-img":"","footer-sml-layout":"","ast-disable-related-posts":"","theme-transparent-header-meta":"","adv-header-id-meta":"","stick-header-meta":"","header-above-stick-meta":"","header-main-stick-meta":"","header-below-stick-meta":"","astra-migrate-meta-layouts":"default","ast-page-background-enabled":"default","ast-page-background-meta":{"desktop":{"background-color":"var(--ast-global-color-4)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""},"tablet":{"background-color":"","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""},"mobile":{"background-color":"","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""}},"ast-content-background-meta":{"desktop":{"background-color":"var(--ast-global-color-5)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""},"tablet":{"background-color":"var(--ast-global-color-5)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""},"mobile":{"background-color":"var(--ast-global-color-5)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""}}},"product_brand":[],"product_cat":[387,384],"product_tag":[237,401,402],"class_list":{"0":"post-18843","1":"product","2":"type-product","3":"status-publish","4":"has-post-thumbnail","6":"product_cat-data-center-ai-system","7":"product_cat-gpu-ai-server","8":"product_tag-ai-","9":"product_tag-server","10":"product_tag-supermicro","11":"desktop-align-left","12":"tablet-align-left","13":"mobile-align-left","15":"first","16":"instock","17":"shipping-taxable","18":"product-type-simple"},"acf":[],"_links":{"self":[{"href":"https:\/\/droneth.or.th\/en\/wp-json\/wp\/v2\/product\/18843","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/droneth.or.th\/en\/wp-json\/wp\/v2\/product"}],"about":[{"href":"https:\/\/droneth.or.th\/en\/wp-json\/wp\/v2\/types\/product"}],"replies":[{"embeddable":true,"href":"https:\/\/droneth.or.th\/en\/wp-json\/wp\/v2\/comments?post=18843"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/droneth.or.th\/en\/wp-json\/wp\/v2\/media\/19183"}],"wp:attachment":[{"href":"https:\/\/droneth.or.th\/en\/wp-json\/wp\/v2\/media?parent=18843"}],"wp:term":[{"taxonomy":"product_brand","embeddable":true,"href":"https:\/\/droneth.or.th\/en\/wp-json\/wp\/v2\/product_brand?post=18843"},{"taxonomy":"product_cat","embeddable":true,"href":"https:\/\/droneth.or.th\/en\/wp-json\/wp\/v2\/product_cat?post=18843"},{"taxonomy":"product_tag","embeddable":true,"href":"https:\/\/droneth.or.th\/en\/wp-json\/wp\/v2\/product_tag?post=18843"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}