--- title: MiniMax M3: Better than Claude and 20X Cheaper? (Open... description: MiniMax M3 is a new open-weights frontier model from Shanghai lab MiniMax, packing 428 billion total parameters (22-23B active via mixture-of-experts) and up... canonical: https://daily.dev/posts/minimax-m3-better-than-claude-and-20x-cheaper-open-source--eqm63nsk9 twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: MiniMax M3: Better than Claude and 20X Cheaper? (Open Source) | daily.dev og:description: MiniMax M3 is a new open-weights frontier model from Shanghai lab MiniMax, packing 428 billion total parameters (22-23B active via mixture-of-experts) and up... og:url: https://daily.dev/posts/minimax-m3-better-than-claude-and-20x-cheaper-open-source--eqm63nsk9 og:image: https://api.daily.dev/og/posts/eqM63NsK9.png og:image:alt: MiniMax M3: Better than Claude and 20X Cheaper? (Open Source) 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. # MiniMax M3: Better than Claude and 20X Cheaper? (Open Source) **[The Coding Gopher](https://daily.dev/sources/codinggopher)** · 9 min read · 36 upvotes · 7 comments ## Summary MiniMax M3 is a new open-weights frontier model from Shanghai lab MiniMax, packing 428 billion total parameters (22-23B active via mixture-of-experts) and up to 1 million tokens of context. It uses a custom sparse attention scheme (MSA) that groups tokens into 128-token hardware-aligned blocks, cutting per-token compute cost at 1M context to roughly 1/20 of the prior M2 model, with 9.7x faster prefill and 15.6x faster decoding. It supports native multimodal understanding including video up to 30 minutes. On benchmarks it scores 59% on SWE-Bench Pro, 66% on Terminal-Bench 2.1, and 83.5% on BrowseComp, beating Claude Opus 4.7's 79.3%. API pricing on OpenRouter launched at 30 cents per million input tokens. Running it locally requires roughly 855GB unquantized, or a minimum of 133GB unified memory even after aggressive 1-bit quantization, putting local hosting out of reach for most individual developers. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### How much memory do I need to run MiniMax M3 locally? Unquantized BF16 weights require about 855 GB of storage. Using extreme 1-bit GGUF quantization shrinks the weights by 85% to around 128 GB, but you still need a minimum of 133 GB of unified memory (RAM plus VRAM) to load the model and its KV cache. For decent performance with 3-bit or 4-bit quantization, expect to need 164 to 270 GB of total memory. _Track hardware requirements for new open-weights model releases like this on daily.dev before committing to a local setup._ ### How does MiniMax M3 compare to Claude Opus 4.7 on benchmarks? MiniMax M3 scored 83.5% on BrowseComp, a multi-step web navigation and data scraping benchmark, beating Claude Opus 4.7's 79.3%. On SWE-Bench Pro it scored 59%, roughly on par with Gemini 3.1 Pro, and it hit 66% on Terminal-Bench 2.1 for sandboxed terminal debugging tasks. _Developers comparing agentic coding models can follow benchmark results like these on daily.dev._ ### What is MiniMax sparse attention (MSA) and why does it make long-context inference cheaper? MiniMax sparse attention avoids evaluating every token in a 1 million token context window by scoring memory with an index branch and pulling only the top K most relevant tokens into SRAM, grouped into hardware-aligned 128-token blocks read sequentially. This cuts per-token compute cost at 1 million tokens to about 1/20 of the previous M2 model, giving a 9.7x prefill speedup and 15.6x decoding speedup. _Engineers optimizing long-context inference costs can follow architecture breakdowns like this on daily.dev._ ## Community discussion Top comments from developers on daily.dev. **@jepudev2** · 10 upvotes > tl;dr: its not **@dash15tonon** · 3 upvotes > You have the official benchmark here [MiniMax M3 - Coding & Agentic Frontier, 1M Context, Multimodal | MiniMax](https://www.minimax.io/models/text/m3) > > I don't think is better than Claude but they can improve it and in a near future they can certainly beat anthropic **@jeremysylvis** · 3 upvotes > I'd like to see it compared to Sonnet 5 - that seems to be what a lot of orgs with Claude EAs are targeting for general enterprise use and general software engineering. > > > M3 _seems_ to be a strong contender in everything except the long horizon stuff, and it seems to be doing as well as anyone that isn't Anthropic/OpenAI. It's certainly got an interesting price point. **@hardik15** · 3 upvotes > What's the use of this comparison and publishing if it's out of reach for indie dev and most of small companies as well. Even after investing this much on hardware the speed and output is still what they were expecting. > > > Also the future versions will need more and more H/w power/configuration unless they achieve SLM in very effective and accurate way **@reachit** · 0 upvotes > It's a bit outdated now. If they can pull it off next time with a big model then they probably can beat Claude, considering that they've only been releasing small models so far. They should learn from Deepseek on how they made flash a beast. --- Tags: [#open-source](https://daily.dev/tags/open-source), [#llm](https://daily.dev/tags/llm), [#mixture-of-experts](https://daily.dev/tags/mixture-of-experts) [View this post on daily.dev](https://daily.dev/posts/minimax-m3-better-than-claude-and-20x-cheaper-open-source--eqm63nsk9) ```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":"MiniMax M3: Better than Claude and 20X Cheaper? (Open Source)","url":"https://daily.dev/posts/minimax-m3-better-than-claude-and-20x-cheaper-open-source--eqm63nsk9","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/minimax-m3-better-than-claude-and-20x-cheaper-open-source--eqm63nsk9"},"datePublished":"2026-08-25T16:05:30.633Z","dateModified":"2026-08-25T16:05:56.586Z","description":"MiniMax M3 is a new open-weights frontier model from Shanghai lab MiniMax, packing 428 billion total parameters (22-23B active via mixture-of-experts) and up...","image":"https://i.ytimg.com/vi/d0P7xoO2gD4/sddefault.jpg","thumbnailUrl":"https://i.ytimg.com/vi/d0P7xoO2gD4/sddefault.jpg","isAccessibleForFree":true,"articleSection":"The Coding Gopher","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":"The Coding Gopher","logo":"https://media.daily.dev/image/upload/s--pv2IKQMG--/f_auto/v1736753456/logos/codinggopher","url":"https://daily.dev/sources/codinggopher"},"commentCount":7,"discussionUrl":"https://daily.dev/posts/minimax-m3-better-than-claude-and-20x-cheaper-open-source--eqm63nsk9","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":36},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":7}],"keywords":"open-source,llm,mixture-of-experts","timeRequired":"PT9M","video":{"@type":"VideoObject","name":"MiniMax M3: Better than Claude and 20X Cheaper? (Open Source)","description":"MiniMax M3 is a new open-weights frontier model from Shanghai lab MiniMax, packing 428 billion total parameters (22-23B active via mixture-of-experts) and up...","thumbnailUrl":"https://i.ytimg.com/vi/d0P7xoO2gD4/sddefault.jpg","uploadDate":"2026-08-25T16:05:30.633Z","duration":"PT9M","url":"https://api.daily.dev/r/eqM63NsK9","embedUrl":"https://www.youtube.com/embed/d0P7xoO2gD4"}} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"The Coding Gopher","item":"https://daily.dev/sources/codinggopher"},{"@type":"ListItem","position":3,"name":"MiniMax M3: Better than Claude and 20X Cheaper? (Open Source)"}]} {"@context":"https://schema.org","@type":"WebPage","@id":"https://daily.dev/posts/minimax-m3-better-than-claude-and-20x-cheaper-open-source--eqm63nsk9","comment":[{"@type":"Comment","text":"tl;dr: its not","datePublished":"2026-08-25T23:17:38.412Z","url":"https://daily.dev/posts/eqM63NsK9#c-hnwEbBMEV","author":{"@type":"Person","name":"jepudev","url":"https://daily.dev/jepudev2","image":"https://avatars.githubusercontent.com/u/71714253?v=4"},"interactionStatistic":{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":10}},{"@type":"Comment","text":"You have the official benchmark here MiniMax M3 - Coding & Agentic Frontier, 1M Context, Multimodal | MiniMax\nI don’t think is better than Claude but they can improve it and in a near future they can certainly beat anthropic","datePublished":"2026-08-26T07:46:48.409Z","dateModified":"2026-08-26T07:48:51.677Z","url":"https://daily.dev/posts/eqM63NsK9#c-OK9iZthsn","author":{"@type":"Person","name":"David15tonon","url":"https://daily.dev/dash15tonon","image":"https://media.daily.dev/image/upload/s--ODg7gW3B--/f_auto/v1779805078/avatars/avatar_I7Oy0mpyXs8dOSJPf3bPC?_a=BAMAMiWQ0"},"interactionStatistic":{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":3}},{"@type":"Comment","text":"I’d like to see it compared to Sonnet 5 - that seems to be what a lot of orgs with Claude EAs are targeting for general enterprise use and general software engineering.\nM3 seems to be a strong contender in everything except the long horizon stuff, and it seems to be doing as well as anyone that isn’t Anthropic/OpenAI. It’s certainly got an interesting price point.","datePublished":"2026-08-26T13:30:04.157Z","url":"https://daily.dev/posts/eqM63NsK9#c-5F6lQD5wh","author":{"@type":"Person","name":"Jeremy Sylvis","url":"https://daily.dev/jeremysylvis","image":"https://avatars.githubusercontent.com/u/58440072?v=4"},"interactionStatistic":{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":3}},{"@type":"Comment","text":"What’s the use of this comparison and publishing if it’s out of reach for indie dev and most of small companies as well. Even after investing this much on hardware the speed and output is still what they were expecting.\nAlso the future versions will need more and more H/w power/configuration unless they achieve SLM in very effective and accurate way","datePublished":"2026-08-26T06:10:10.474Z","url":"https://daily.dev/posts/eqM63NsK9#c-dpib7Hzab","author":{"@type":"Person","name":"Hardik","url":"https://daily.dev/hardik15","image":"https://media.daily.dev/image/upload/s--O0TOmw4y--/f_auto/v1715772965/public/noProfile"},"interactionStatistic":{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":3}},{"@type":"Comment","text":"It’s a bit outdated now. If they can pull it off next time with a big model then they probably can beat Claude, considering that they’ve only been releasing small models so far. They should learn from Deepseek on how they made flash a beast.","datePublished":"2026-08-27T23:02:30.009Z","url":"https://daily.dev/posts/eqM63NsK9#c-ojZbkrxuT","author":{"@type":"Person","name":"Neil","url":"https://daily.dev/reachit","image":"https://avatars.githubusercontent.com/u/140867360?v=4"}}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/minimax-m3-better-than-claude-and-20x-cheaper-open-source--eqm63nsk9#faq","mainEntity":[{"@type":"Question","name":"How much memory do I need to run MiniMax M3 locally?","acceptedAnswer":{"@type":"Answer","text":"Unquantized BF16 weights require about 855 GB of storage. Using extreme 1-bit GGUF quantization shrinks the weights by 85% to around 128 GB, but you still need a minimum of 133 GB of unified memory (RAM plus VRAM) to load the model and its KV cache. For decent performance with 3-bit or 4-bit quantization, expect to need 164 to 270 GB of total memory. Track hardware requirements for new open-weights model releases like this on daily.dev before committing to a local setup."}},{"@type":"Question","name":"How does MiniMax M3 compare to Claude Opus 4.7 on benchmarks?","acceptedAnswer":{"@type":"Answer","text":"MiniMax M3 scored 83.5% on BrowseComp, a multi-step web navigation and data scraping benchmark, beating Claude Opus 4.7's 79.3%. On SWE-Bench Pro it scored 59%, roughly on par with Gemini 3.1 Pro, and it hit 66% on Terminal-Bench 2.1 for sandboxed terminal debugging tasks. Developers comparing agentic coding models can follow benchmark results like these on daily.dev."}},{"@type":"Question","name":"What is MiniMax sparse attention (MSA) and why does it make long-context inference cheaper?","acceptedAnswer":{"@type":"Answer","text":"MiniMax sparse attention avoids evaluating every token in a 1 million token context window by scoring memory with an index branch and pulling only the top K most relevant tokens into SRAM, grouped into hardware-aligned 128-token blocks read sequentially. This cuts per-token compute cost at 1 million tokens to about 1/20 of the previous M2 model, giving a 9.7x prefill speedup and 15.6x decoding speedup. Engineers optimizing long-context inference costs can follow architecture breakdowns like this on daily.dev."}}]} ```