--- title: Faster Diffusion on Blackwell: MXFP8 and NVFP4 with... description: MXFP8 and NVFP4 microscaling quantization formats natively supported by NVIDIA's Blackwell architecture (B200 GPUs) deliver significant inference speedups for... canonical: https://daily.dev/posts/faster-diffusion-on-blackwell-mxfp8-and-nvfp4-with-diffusers-and-torchao-pytorch-i2hn4mzkr twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Faster Diffusion on Blackwell: MXFP8 and NVFP4 with Diffusers and TorchAO – PyTorch | daily.dev og:description: MXFP8 and NVFP4 microscaling quantization formats natively supported by NVIDIA's Blackwell architecture (B200 GPUs) deliver significant inference speedups for... og:url: https://daily.dev/posts/faster-diffusion-on-blackwell-mxfp8-and-nvfp4-with-diffusers-and-torchao-pytorch-i2hn4mzkr og:image: https://api.daily.dev/og/posts/I2hn4MzKR.png og:image:alt: Faster Diffusion on Blackwell: MXFP8 and NVFP4 with Diffusers and TorchAO – PyTorch og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # Faster Diffusion on Blackwell: MXFP8 and NVFP4 with Diffusers and TorchAO – PyTorch **[PyTorch](https://daily.dev/sources/pytorch)** · 12 min read · 0 upvotes · 0 comments ## Summary MXFP8 and NVFP4 microscaling quantization formats natively supported by NVIDIA's Blackwell architecture (B200 GPUs) deliver significant inference speedups for diffusion models. Using diffusers and TorchAO, benchmarks on Flux.1-Dev, QwenImage, and LTX-2 show up to 1.26x speedup with MXFP8 and up to 1.68x with NVFP4 compared to BF16 baselines, while also reducing peak memory by up to ~3.5x. The post covers selective quantization strategies (skipping small or accuracy-critical layers), CUDA Graphs via torch.compile reduce-overhead mode to cut CPU overhead at small batch sizes, and LPIPS as a perceptual accuracy metric. Code and reproducible recipes are provided for all three models. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Similar posts on daily.dev - [Scaling NVFP4 Inference for FLUX.2 on NVIDIA Blackwell Data Center GPUs](https://daily.dev/posts/scaling-nvfp4-inference-for-flux-2-on-nvidia-blackwell-data-center-gpus-o6ceqm1vc) · NVIDIA Developer · 1 upvotes · 0 comments - [MXFP8 Training for MoEs: 1.3x training speedup vs BF16 for Llama4 Scout on GB200 cluster using TorchAO and TorchTitan – PyTorch](https://daily.dev/posts/mxfp8-training-for-moes-1-3x-training-speedup-vs-bf16-for-llama4-scout-on-gb200-cluster-using-torch-agasmbqcx) · PyTorch · 0 upvotes · 0 comments - [Bringing Nunchaku 4-bit Diffusion Inference to Diffusers](https://daily.dev/posts/bringing-nunchaku-4-bit-diffusion-inference-to-diffusers-52bez8xcq) · Hugging Face · 0 upvotes · 0 comments - [Train Models Faster with JAX and MaxText Using NVFP4 on NVIDIA Blackwell](https://daily.dev/posts/train-models-faster-with-jax-and-maxtext-using-nvfp4-on-nvidia-blackwell-ouytd5oyn) · NVIDIA Developer · 0 upvotes · 0 comments --- Tags: [#data-science](https://daily.dev/tags/data-science), [#pytorch](https://daily.dev/tags/pytorch), [#diffusion-models](https://daily.dev/tags/diffusion-models) [View this post on daily.dev](https://daily.dev/posts/faster-diffusion-on-blackwell-mxfp8-and-nvfp4-with-diffusers-and-torchao-pytorch-i2hn4mzkr) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"Faster Diffusion on Blackwell: MXFP8 and NVFP4 with Diffusers and TorchAO – PyTorch","url":"https://daily.dev/posts/faster-diffusion-on-blackwell-mxfp8-and-nvfp4-with-diffusers-and-torchao-pytorch-i2hn4mzkr","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/faster-diffusion-on-blackwell-mxfp8-and-nvfp4-with-diffusers-and-torchao-pytorch-i2hn4mzkr"},"datePublished":"2026-04-08T16:42:59.849Z","dateModified":"2026-04-08T16:43:22.432Z","description":"MXFP8 and NVFP4 microscaling quantization formats natively supported by NVIDIA's Blackwell architecture (B200 GPUs) deliver significant inference speedups for...","image":"https://media.daily.dev/image/upload/s--58gMhC4P--/f_auto/v1722860399/public/Placeholder%2012","thumbnailUrl":"https://media.daily.dev/image/upload/s--58gMhC4P--/f_auto/v1722860399/public/Placeholder%2012","isAccessibleForFree":true,"articleSection":"PyTorch","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"PyTorch","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/5fdab3d75a834a97a52d433d9c7e5ff9","url":"https://daily.dev/sources/pytorch"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/faster-diffusion-on-blackwell-mxfp8-and-nvfp4-with-diffusers-and-torchao-pytorch-i2hn4mzkr","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"data-science,pytorch,diffusion-models","timeRequired":"PT12M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"PyTorch","item":"https://daily.dev/sources/pytorch"},{"@type":"ListItem","position":3,"name":"Faster Diffusion on Blackwell: MXFP8 and NVFP4 with Diffusers and TorchAO – PyTorch"}]} ```