--- title: Run DiffusionGemma on NVIDIA for Developer-Ready,... description: DiffusionGemma, developed by Google DeepMind and optimized by NVIDIA, uses diffusion-based denoising to generate 256 tokens in parallel per step rather than... canonical: https://daily.dev/posts/run-diffusiongemma-on-nvidia-for-developer-ready-high-throughput-text-generation-mrq2nzn8v twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Run DiffusionGemma on NVIDIA for Developer-Ready, High-Throughput Text Generation | daily.dev og:description: DiffusionGemma, developed by Google DeepMind and optimized by NVIDIA, uses diffusion-based denoising to generate 256 tokens in parallel per step rather than... og:url: https://daily.dev/posts/run-diffusiongemma-on-nvidia-for-developer-ready-high-throughput-text-generation-mrq2nzn8v og:image: https://api.daily.dev/og/posts/mRq2NZN8V.png og:image:alt: Run DiffusionGemma on NVIDIA for Developer-Ready, High-Throughput Text Generation 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. # Run DiffusionGemma on NVIDIA for Developer-Ready, High-Throughput Text Generation **[NVIDIA Developer](https://daily.dev/sources/nvidiadev)** · 4 min read · 0 upvotes · 0 comments ## Summary DiffusionGemma, developed by Google DeepMind and optimized by NVIDIA, uses diffusion-based denoising to generate 256 tokens in parallel per step rather than sequentially. It achieves up to 1,000 tokens/sec on a single H100 GPU and 150 tokens/sec on DGX Spark. Built on the Gemma 4 26B MoE architecture with 3.8B active parameters, it supports BF16 and NVFP4 precision. Developers can access it via Hugging Face Transformers for prototyping, vLLM for high-throughput serving, or NVIDIA NIM for containerized production deployment with an OpenAI-compatible API. Fine-tuning is available through NVIDIA NeMo Framework. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Similar posts on daily.dev - [NVIDIA Accelerates Google DeepMind’s DiffusionGemma for Local AI](https://daily.dev/posts/nvidia-accelerates-google-deepmind-s-diffusiongemma-for-local-ai-xcxwdxism) · NVIDIA · 0 upvotes · 0 comments - [Google’s DiffusionGemma is 4x faster than its other Gemma models](https://daily.dev/posts/google-s-diffusiongemma-is-4x-faster-than-its-other-gemma-models-vjw4zukla) · The New Stack · 2 upvotes · 0 comments - [DiffusionGemma: 4x faster text generation](https://daily.dev/posts/diffusiongemma-4x-faster-text-generation-yowvfywbx) · DeepMind · 1 upvotes · 0 comments --- Tags: [#nvidia](https://daily.dev/tags/nvidia), [#text-generation](https://daily.dev/tags/text-generation), [#vllm](https://daily.dev/tags/vllm) [View this post on daily.dev](https://daily.dev/posts/run-diffusiongemma-on-nvidia-for-developer-ready-high-throughput-text-generation-mrq2nzn8v) ```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":"Run DiffusionGemma on NVIDIA for Developer-Ready, High-Throughput Text Generation","url":"https://daily.dev/posts/run-diffusiongemma-on-nvidia-for-developer-ready-high-throughput-text-generation-mrq2nzn8v","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/run-diffusiongemma-on-nvidia-for-developer-ready-high-throughput-text-generation-mrq2nzn8v"},"datePublished":"2026-06-10T16:21:15.183Z","dateModified":"2026-06-10T16:21:42.913Z","description":"DiffusionGemma, developed by Google DeepMind and optimized by NVIDIA, uses diffusion-based denoising to generate 256 tokens in parallel per step rather than...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/58a11a9a4132770a08479543e4eb3b38?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/58a11a9a4132770a08479543e4eb3b38?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"NVIDIA Developer","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":"NVIDIA Developer","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/86e45aab42ba48ce83103d01b1119910","url":"https://daily.dev/sources/nvidiadev"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/run-diffusiongemma-on-nvidia-for-developer-ready-high-throughput-text-generation-mrq2nzn8v","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"nvidia,text-generation,vllm","timeRequired":"PT4M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"NVIDIA Developer","item":"https://daily.dev/sources/nvidiadev"},{"@type":"ListItem","position":3,"name":"Run DiffusionGemma on NVIDIA for Developer-Ready, High-Throughput Text Generation"}]} ```