NVIDIA B200 vs B300
Specs below are from NVIDIA's own spec sheets; rental prices are from each cloud's own price list. 6 of the GPU clouds tracked here price at least one of the two, and 5 price both.
Specifications
Each card's flagship server variant as NVIDIA names it, figures as NVIDIA prints them. B200: Per-system figures for an eight-GPU NVIDIA HGX B200 board, from the specifications table on NVIDIA's HGX platform page, which prints no per-GPU figures except NVLink GPU-to-GPU bandwidth; where NVIDIA prints one figure for two precisions (FP8/FP6, FP16/BF16, FP64/FP64 Tensor Core) it is recorded under each. Figures marked ¹ are shown sparse | dense and figures marked ² are sparse, with dense half the figure shown, as NVIDIA's footnotes state. B300: Per-system figures for an eight-GPU NVIDIA HGX B300 board, from the specifications table on NVIDIA's HGX platform page, which prints no per-GPU figures except NVLink GPU-to-GPU bandwidth; where NVIDIA prints one figure for two precisions (FP8/FP6, FP16/BF16, FP64/FP64 Tensor Core) it is recorded under each. Figures marked ¹ are shown sparse | dense and figures marked ² are sparse, with dense half the figure shown, as NVIDIA's footnotes state.
| Spec | HGX B200 (8 GPUs) | HGX B300 (8 GPUs) |
|---|---|---|
| GPU memory | 1.4 TB | 2.1 TB |
| FP4 Tensor Core | 144 PFLOPS | 72 PFLOPS¹ | 144 PFLOPS | 108 PFLOPS¹ |
| FP6 Tensor Core | 72 PFLOPS² | 72 PFLOPS² |
| FP8 Tensor Core | 72 PFLOPS² | 72 PFLOPS² |
| INT8 Tensor Core | 72 POPS² | 3 POPS² |
| FP16 Tensor Core | 36 PFLOPS² | 36 PFLOPS² |
| BF16 Tensor Core | 36 PFLOPS² | 36 PFLOPS² |
| TF32 Tensor Core | 18 PFLOPS² | 18 PFLOPS² |
| FP32 | 600 TFLOPS | 600 TFLOPS |
| FP64 Tensor Core | 296 TFLOPS | 10 TFLOPS |
| FP64 | 296 TFLOPS | 10 TFLOPS |
| Interconnect | NVIDIA NVLink Fifth generation; NVLink GPU-to-GPU Bandwidth 1.8 TB/s; Total NVLink Bandwidth 14.4 TB/s | NVIDIA NVLink Fifth generation; NVLink GPU-to-GPU Bandwidth 1.8 TB/s; Total NVLink Bandwidth 14.4 TB/s |
| Form factor | 8x NVIDIA Blackwell SXM | 8x NVIDIA Blackwell Ultra SXM |
What renting each costs
Hourly on-demand prices from each cloud's own price list, alphabetical by cloud and not ranked: some price per GPU and others a whole multi-GPU node, and the unit is on every figure. Clouds that rent only one of the two show a dash for the other.
| Cloud | B200 | B300 |
|---|---|---|
| CoreWeave | NVIDIA HGX B200: $68.80 for 8 GPUs 27 Sept | NVIDIA HGX B300: $35.84 for 8 GPUs 27 Sept |
| Hyperstack | NVIDIA B200: $6.00 per GPU 27 Sept | NVIDIA B300: $7.40 per GPU 27 Sept |
| Lambda | NVIDIA B200 SXM6: $6.99 per GPU 27 Sept | — |
| Nebius AI Cloud | NVIDIA HGX B200: $7.15 per GPU 27 Sept | NVIDIA HGX B300: $7.85 per GPU 27 Sept |
| RunPod | B200: $6.79 per GPU 27 Sept | B300: $7.89 per GPU 27 Sept |
| Vast.ai | B200: $6.25 per GPU 27 Sept | B300: $8.75 per GPU 27 Sept |