--- title: What LLM quantization works best for you? Q4_K_S or Q4_K_M description: Quantization methods for LLM, including Q3_K_S, Q4_K_M, Q4_0, and Q8_0, are discussed. The K_M models are recommended for their balance between size and... canonical: https://daily.dev/posts/what-llm-quantization-works-best-for-you-q4-k-s-or-q4-k-m-jabfgq2xn twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: What LLM quantization works best for you? Q4_K_S or Q4_K_M | daily.dev og:description: Quantization methods for LLM, including Q3_K_S, Q4_K_M, Q4_0, and Q8_0, are discussed. The K_M models are recommended for their balance between size and... og:url: https://daily.dev/posts/what-llm-quantization-works-best-for-you-q4-k-s-or-q4-k-m-jabfgq2xn og:image: https://api.daily.dev/og/posts/JAbFgQ2xn.png og:image:alt: What LLM quantization works best for you? Q4_K_S or Q4_K_M 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. # What LLM quantization works best for you? Q4_K_S or Q4_K_M **[GoPenAI](https://daily.dev/sources/gopenai)** · 1 min read · 1 upvotes · 0 comments ## Summary Quantization methods for LLM, including Q3_K_S, Q4_K_M, Q4_0, and Q8_0, are discussed. The K_M models are recommended for their balance between size and perplexity. Implementation details of llama.cpp for quantization are provided. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: --- Tags: [#c++](https://daily.dev/tags/c++), [#machine-learning](https://daily.dev/tags/machine-learning), [#performance](https://daily.dev/tags/performance) [View this post on daily.dev](https://daily.dev/posts/what-llm-quantization-works-best-for-you-q4-k-s-or-q4-k-m-jabfgq2xn) ```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":"What LLM quantization works best for you? Q4_K_S or Q4_K_M","url":"https://daily.dev/posts/what-llm-quantization-works-best-for-you-q4-k-s-or-q4-k-m-jabfgq2xn","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/what-llm-quantization-works-best-for-you-q4-k-s-or-q4-k-m-jabfgq2xn"},"datePublished":"2024-05-03T11:23:28.346Z","dateModified":"2026-03-15T05:52:00.405Z","description":"Quantization methods for LLM, including Q3_K_S, Q4_K_M, Q4_0, and Q8_0, are discussed. The K_M models are recommended for their balance between size and...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/f95ae3c5475be238680ed7f1d96ef57e?_a=AQAEuiZ","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/f95ae3c5475be238680ed7f1d96ef57e?_a=AQAEuiZ","isAccessibleForFree":true,"articleSection":"GoPenAI","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":"GoPenAI","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/f34dfd0c312c4a59b897eb64ad28d895","url":"https://daily.dev/sources/gopenai"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/what-llm-quantization-works-best-for-you-q4-k-s-or-q4-k-m-jabfgq2xn","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":1},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"c++,machine-learning,performance","timeRequired":"PT1M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"GoPenAI","item":"https://daily.dev/sources/gopenai"},{"@type":"ListItem","position":3,"name":"What LLM quantization works best for you? Q4_K_S or Q4_K_M"}]} ```