NVIDIA B300 (Blackwell Ultra) · Blackwell Ultra

BF16, dense

2,200 TFLOPS FP16/BF16 Tensor Core Dense/Sparse 2.2/4.5 petaFLOPS 2.2/4.5 petaFLOPS NVIDIA Blackwell Architecture Technical Brief (V2.1) (2.2 PFLOPS on the page; read from a table with a column for each product, whose head reads “Table 3. System Specifications for HGX B300 and HGX B200 HGX B300 HGX B200”)

FP8, dense

4,500 TFLOPS FP8/FP6 Tensor Core Dense/Sparse 4.5/9 petaFLOPS 4.5/9 petaFLOPS NVIDIA Blackwell Architecture Technical Brief (V2.1) (4.5 PFLOPS on the page; read from a table with a column for each product, whose head reads “Table 3. System Specifications for HGX B300 and HGX B200 HGX B300 HGX B200”)

FP4, dense

14,000 TFLOPS FP4 Tensor Core Dense/Sparse 14/18 petaFLOPS 9/18 petaFLOPS NVIDIA Blackwell Architecture Technical Brief (V2.1) (14 PFLOPS on the page; read from a table with a column for each product, whose head reads “Table 3. System Specifications for HGX B300 and HGX B200 HGX B300 HGX B200”)

Memory

270 GB 270 GB HBM3e | 7.7 TB/s Up to 192 GB HBM3e | 7.7 TB/s NVIDIA Blackwell Architecture Technical Brief (V2.1) (read from a table with a column for each product, whose head reads “Table 3. System Specifications for HGX B300 and HGX B200 HGX B300 HGX B200”)

Memory bandwidth

7.7 TB/s 270 GB HBM3e | 7.7 TB/s Up to 192 GB HBM3e | 7.7 TB/s NVIDIA Blackwell Architecture Technical Brief (V2.1) (read from a table with a column for each product, whose head reads “Table 3. System Specifications for HGX B300 and HGX B200 HGX B300 HGX B200”)

Maximum power

1,100 W Max thermal design power (TDP) 1100 W 1000W NVIDIA Blackwell Architecture Technical Brief (V2.1) (read from a table with a column for each product, whose head reads “Table 3. System Specifications for HGX B300 and HGX B200 HGX B300 HGX B200”)

Compute per watt

2,000 GFLOPS/Wdense BF16 over maximum power; 4,091 GFLOPS/W at FP8

Per-GPU figures are for the HGX B300 GPU (first column of the table): 270 GB usable HBM3e. The GB300 NVL72 version of the GPU is rated higher (279 GB, 8 TB/s, up to 1,400 W in the Blackwell Ultra datasheet).

1. 18 Mar 2025 Promised Blackwell Ultra-based products expected from partners from the second half of 2025 in the second half of 2025. Blackwell Ultra-based products are expected to be available from partners starting from the second half of 2025. NVIDIA Blackwell Ultra AI Factory Platform Paves Way for Age of AI Reasoning
2. 27 Aug 2025 Shipped: Blackwell Ultra production ramping at full speed. production of Blackwell Ultra is ramping at full speed, and demand is extraordinary NVIDIA Announces Financial Results for Second Quarter Fiscal 2026

Epoch AI’s names for this chip: B300.

• Tesla V100 SXM2 417 gigaflops of dense FP16 compute per watt, at 300 W
• A100 SXM 80GB 780 gigaflops of dense BF16 compute per watt, at 400 W
• H100 SXM 1,414 gigaflops of dense BF16 compute per watt, at 700 W
• H200 SXM 1,414 gigaflops of dense BF16 compute per watt, at 700 W
• GH200 Grace Hopper Superchip 990 gigaflops of dense BF16 compute per watt, at 1,000 W
• B200 2,200 gigaflops of dense BF16 compute per watt, at 1,000 W
• GB200 Grace Blackwell Superchip 5,000 teraflops of dense BF16 compute a chip; NVIDIA publishes no power figure
• Rubin GPU 4,000 teraflops of dense BF16 compute a chip; NVIDIA publishes no power figure