Excerpt of the Hugging Face model card BennyDaBall/Fibo-2.0-dev-NVFP4 (revision e8e06008), section 'The Numbers' (author's own figures, not measured by us):

Same machine, same graph (core nodes only: Load Diffusion Model, Load CLIP `fibo2`, TextEncodeFibo2, KSampler euler / simple, 50 steps, CFG 5, VAE Decode). Speed is ComfyUI's own execution time per image, median of 4-6 warm runs with a fresh seed every run. Peak VRAM is the whole GPU (bf16 text encoder, VAE and my desktop included).

| Model | File | s/img 1024x1024 | s/img 1920x1088 | Peak VRAM (1024) |
|---|---|---|---|---|
| bf16 (Comfy-Org) | 16.45 GB | 39.78 | 84.94 | 27.9 GB |
| int8 ConvRot (Comfy-Org) | 8.41 GB | 16.86 | 36.03 | 21.3 GB |
| **NVFP4 (this repo)** | **7.27 GB** | **15.68** | **33.93** | **20.3 GB** |

So: **2.5x faster than bf16, 7% faster than int8, 56% smaller than bf16, 14% smaller than int8.**

Header line of the same card (line 28):
**One file. 7.27 GB. 2.5x faster than bf16 on an RTX 5090, and faster and smaller than the int8 build too.**