--- title: Multi-token-prediction in Gemma 4 | daily.dev description: Google has released Multi-Token Prediction (MTP) drafters for the Gemma 4 model family, enabling up to 3x faster inference through speculative decoding without... canonical: https://daily.dev/posts/multi-token-prediction-in-gemma-4-p8wqk64sp twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Multi-token-prediction in Gemma 4 | daily.dev og:description: Google has released Multi-Token Prediction (MTP) drafters for the Gemma 4 model family, enabling up to 3x faster inference through speculative decoding without... og:url: https://daily.dev/posts/multi-token-prediction-in-gemma-4-p8wqk64sp og:image: https://api.daily.dev/og/posts/p8wQK64sp.png og:image:alt: Multi-token-prediction in Gemma 4 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. # Multi-token-prediction in Gemma 4 **[Hacker News](https://daily.dev/sources/hn)** · 5 min read · 1 upvotes · 0 comments ## Summary Google has released Multi-Token Prediction (MTP) drafters for the Gemma 4 model family, enabling up to 3x faster inference through speculative decoding without any quality degradation. The technique pairs a lightweight drafter model with the heavier target model: the drafter predicts multiple future tokens in parallel, and the target model verifies them in a single forward pass. This approach addresses the memory-bandwidth bottleneck inherent in standard autoregressive LLM inference. MTP drafters share the target model's KV cache and activations, avoiding redundant computation. Additional optimizations include an efficient embedding clustering technique for edge models (E2B/E4B) and hardware-specific tuning for Apple Silicon and NVIDIA GPUs. The drafters are available under Apache 2.0 on Hugging Face, Kaggle, and supported by vLLM, MLX, SGLang, and Ollama. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Similar posts on daily.dev - [Gemma 4 Multi-Token Prediction Delivers Up to ~3x Faster Token Generation](https://daily.dev/posts/gemma-4-multi-token-prediction-delivers-up-to-3x-faster-token-generation-n9rqcmn5a) · InfoQ · 1 upvotes · 0 comments - [Multi-token prediction technique triples LLM inference speed without auxiliary draft models](https://daily.dev/posts/multi-token-prediction-technique-triples-llm-inference-speed-without-auxiliary-draft-models-hxaajvily) · InfoWorld · 1 upvotes · 0 comments - [The Machine Learning Practitioner’s Guide to Speculative Decoding](https://daily.dev/posts/the-machine-learning-practitioner-s-guide-to-speculative-decoding-3z4bou5te) · Machine Learning Mastery · 2 upvotes · 0 comments - [Why We’ve Been Optimizing the Wrong Thing in LLMs for Years](https://daily.dev/posts/why-we-ve-been-optimizing-the-wrong-thing-in-llms-for-years-sgoikytic) · Towards Data Science · 2 upvotes · 0 comments --- Tags: [#llm](https://daily.dev/tags/llm), [#ai-inference](https://daily.dev/tags/ai-inference), [#gemma](https://daily.dev/tags/gemma) [View this post on daily.dev](https://daily.dev/posts/multi-token-prediction-in-gemma-4-p8wqk64sp) ```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":"Multi-token-prediction in Gemma 4","url":"https://daily.dev/posts/multi-token-prediction-in-gemma-4-p8wqk64sp","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/multi-token-prediction-in-gemma-4-p8wqk64sp"},"datePublished":"2026-05-05T17:55:25.939Z","dateModified":"2026-05-10T09:49:54.469Z","description":"Google has released Multi-Token Prediction (MTP) drafters for the Gemma 4 model family, enabling up to 3x faster inference through speculative decoding without...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/024dbd798852c6a650e3bad6cfbf31bf?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/024dbd798852c6a650e3bad6cfbf31bf?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"Hacker News","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":"Hacker News","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/hn","url":"https://daily.dev/sources/hn"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/multi-token-prediction-in-gemma-4-p8wqk64sp","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":1},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"llm,ai-inference,gemma","timeRequired":"PT5M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Hacker News","item":"https://daily.dev/sources/hn"},{"@type":"ListItem","position":3,"name":"Multi-token-prediction in Gemma 4"}]} ```