--- title: Accelerating LLM inference with post-training weight and... description: Post-training quantization (PTQ) techniques like AWQ and GPTQ compress LLM weights from 16/32-bit to 4/8-bit integers, reducing model size by 2-8x without... canonical: https://daily.dev/posts/accelerating-llm-inference-with-post-training-weight-and-activation-using-awq-and-gptq-on-amazon-sag-jbmt9237k twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Accelerating LLM inference with post-training weight and activation using AWQ and GPTQ on Amazon SageMaker AI | daily.dev og:description: Post-training quantization (PTQ) techniques like AWQ and GPTQ compress LLM weights from 16/32-bit to 4/8-bit integers, reducing model size by 2-8x without... og:url: https://daily.dev/posts/accelerating-llm-inference-with-post-training-weight-and-activation-using-awq-and-gptq-on-amazon-sag-jbmt9237k og:image: https://api.daily.dev/og/posts/JBmt9237K.png og:image:alt: Accelerating LLM inference with post-training weight and activation using AWQ and GPTQ on Amazon SageMaker AI 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. # Accelerating LLM inference with post-training weight and activation using AWQ and GPTQ on Amazon SageMaker AI **[AWS](https://daily.dev/sources/aws)** · 30 min read · 3 upvotes · 0 comments ## Summary Post-training quantization (PTQ) techniques like AWQ and GPTQ compress LLM weights from 16/32-bit to 4/8-bit integers, reducing model size by 2-8x without retraining. This enables deploying massive models (like DeepSeek-V3 or Llama 3.1 70B) on smaller GPU instances while maintaining near-original accuracy. The article explains weight/activation quantization strategies (W4A16, W8A8, etc.), compares AWQ's activation-aware scaling against GPTQ's error-compensation approach, and demonstrates implementation on Amazon SageMaker using vLLM and llm-compressor. Benchmark results across three models show 30-70% memory reduction, 2-3x latency improvements, and higher throughput at scale, making state-of-the-art LLMs production-viable. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Similar posts on daily.dev - [Understanding W8A8 INT8 LLM quantization: Half the size, better performance, same accuracy](https://daily.dev/posts/understanding-w8a8-int8-llm-quantization-half-the-size-better-performance-same-accuracy-o3xrxutco) · Red Hat Developer · 0 upvotes · 0 comments - [LLM quantization guide: How to do it, and how it helps](https://daily.dev/posts/llm-quantization-guide-how-to-do-it-and-how-it-helps-ibtxb1uok) · Red Hat Developer · 0 upvotes · 0 comments - [The LLM Inference Optimization Stack: From Quantization to Speculative Decoding Part 1](https://daily.dev/posts/the-llm-inference-optimization-stack-from-quantization-to-speculative-decoding-part-1-ryexzxqsr) · DigitalOcean Community · 0 upvotes · 0 comments --- Tags: [#machine-learning](https://daily.dev/tags/machine-learning), [#aws](https://daily.dev/tags/aws), [#llm](https://daily.dev/tags/llm), [#aws-sagemaker](https://daily.dev/tags/aws-sagemaker) [View this post on daily.dev](https://daily.dev/posts/accelerating-llm-inference-with-post-training-weight-and-activation-using-awq-and-gptq-on-amazon-sag-jbmt9237k) ```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":"Accelerating LLM inference with post-training weight and activation using AWQ and GPTQ on Amazon SageMaker AI","url":"https://daily.dev/posts/accelerating-llm-inference-with-post-training-weight-and-activation-using-awq-and-gptq-on-amazon-sag-jbmt9237k","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/accelerating-llm-inference-with-post-training-weight-and-activation-using-awq-and-gptq-on-amazon-sag-jbmt9237k"},"datePublished":"2026-01-09T18:17:48.806Z","dateModified":"2026-01-09T18:18:16.587Z","description":"Post-training quantization (PTQ) techniques like AWQ and GPTQ compress LLM weights from 16/32-bit to 4/8-bit integers, reducing model size by 2-8x without...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/215ad6ff2f60a19977a06054edb168f1?_a=AQAEulh","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/215ad6ff2f60a19977a06054edb168f1?_a=AQAEulh","isAccessibleForFree":true,"articleSection":"AWS","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":"AWS","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/aws","url":"https://daily.dev/sources/aws"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/accelerating-llm-inference-with-post-training-weight-and-activation-using-awq-and-gptq-on-amazon-sag-jbmt9237k","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":3},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"machine-learning,aws,llm,aws-sagemaker","timeRequired":"PT30M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"AWS","item":"https://daily.dev/sources/aws"},{"@type":"ListItem","position":3,"name":"Accelerating LLM inference with post-training weight and activation using AWQ and GPTQ on Amazon SageMaker AI"}]} ```