---
title: Machine setup (GPU)
slug: machine-setup-gpu
docTags: 
createdAt: 2025-12-29T23:06:46.950Z
---

Floyo runs on NVIDIA **H100 NVL** GPUs. Each H100 NVL delivers **3.9 TB/s** of HBM3 memory bandwidth - **over 2x **the bandwidth of RTX PRO 6000 GPUs - which helps workflows run faster, especially for higher-res generations, larger models, and longer videos



|                        | **H100 NVL**        | **RTX PRO 6000** | **RTX 5090** | **What it means (AI/ML workflows)**                                                                                                                                                                                                                                                                                                                                           |
| ---------------------- | ------------------- | ---------------- | ------------ | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| **Memory Type & Size** | 94GB **HBM3&#xA0;** | 96GB *GDDR7*     | 32GB *GDDR7* | **HBM3 vs GDDR7:** <br />HBM3 is “on-package” stacked memory built for extreme speed.<br />GDDR7 is fast memory chips on the board, but with less bandwidth than HBM setups.                                                                                                                                                                                                  |
| **Memory bandwidth**   | **3.938 TB/s**      | 1.792 TB/s       | 1.792 TB/s   | **Bandwidth = how fast the GPU can read/write VRAM.** Diffusion/video workflows move a ton of data every step. When bandwidth is the limiter, higher bandwidth directly translates to faster steps and better throughput (especially big images, long video, and multi-model workflows).<br />H100 NVL has **\~2.2x higher memory bandwidth** than RTX PRO 6000 and RTX 5090. |
| **FP8 Tensor&#xA0;**   | **3,341 TFLOPS**    | 2,015 TFLOPS     | 1,676 TFLOPS | Think of this as “top-end AI math speed” when a workflow/runtime can use FP8. If a workflow is FP8-optimized (**quantized**), higher FP8 mean more images/frames per minute. H100 leads by a lot here.                                                                                                                                                                        |
| **FP16 Tensor&#xA0;**  | **1,671 TFLOPS**    | 1,008 TFLOPS     | 838 TFLOPS   | **Most open-source image/video generation inference runs in FP16/BF16 today.** This often tracks real-world speed for diffusion steps. H100 is materially ahead, which is why we standardize on H100 NVL for predictable, fast workflow runs.                                                                                                                                 |
| **TF32 Tensor**        | **835 TFLOPS**      | 504 TFLOPS       | 210 TFLOPS   | **Mostly relevant to training/fine-tuning** and some mixed-precision training paths - less important for typical “run a workflow and generate” inference.                                                                                                                                                                                                                     |



Tensor TFLOPS are peak theoretical values shown with “sparsity” where applicable; real-world speed varies by model, precision/quantization, and which part of the workflow is the bottleneck (often memory bandwidth for diffusion/video).