--- title: What “open weights” means for AI models | daily.dev description: Explains the difference between open weights, open access, and open-source AI, arguing that downloadable model parameters are not the same as a fully... canonical: https://daily.dev/posts/what-open-weights-means-for-ai-models-6vljntk5i twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: What “open weights” means for AI models | daily.dev og:description: Explains the difference between open weights, open access, and open-source AI, arguing that downloadable model parameters are not the same as a fully... og:url: https://daily.dev/posts/what-open-weights-means-for-ai-models-6vljntk5i og:image: https://api.daily.dev/og/posts/6vlJntk5i.png og:image:alt: What “open weights” means for AI models 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 “open weights” means for AI models **[Flavio Copes](https://daily.dev/sources/flaviocopes)** · 13 min read · 38 upvotes · 2 comments ## Summary Explains the difference between open weights, open access, and open-source AI, arguing that downloadable model parameters are not the same as a fully reproducible, open system. Covers what weights are, what's needed to run a model (tokenizer, config, inference code), the practical benefits of open weights (local execution, provider choice, quantization, fine-tuning, version stability), and why licensing terms matter as much as availability. Uses the announced Qwen3.8 (up to 2.4 trillion parameters) and Moonshot's Kimi K3 (2.8 trillion parameters, mixture-of-experts, 1M-token context) as examples of massive open-weight releases that are technically open but impractical for most people to self-host. Ends with a ten-point checklist for evaluating any 'open' model announcement. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### What is the difference between open weights and open-source AI for a model? Open weights means the trained parameters are downloadable so you can run, fine-tune, or quantize the model, but the training code, full dataset information, and reproducibility are not guaranteed. Open-source AI, per the Open Source Initiative's definition, requires weights plus the preferred materials needed to study and modify the system, including training code and enough data information to substantially recreate it. _daily.dev readers weighing model licensing tradeoffs can dig into definitions like these before picking a model to deploy._ ### How many parameters does Kimi K3 have and what is its architecture? Kimi K3 has 2.8 trillion total parameters using a mixture-of-experts architecture with 896 experts, activating only 16 per token, which makes inference more efficient than using all parameters every time. It offers native vision and a 1-million-token context window. Moonshot AI announced it on July 16, 2026, and said full weights would release by July 27, 2026, recommending deployments with 64 or more accelerators. _Teams sizing hardware for massive mixture-of-experts models can track releases like this one on daily.dev._ ### How many parameters does Qwen3.8 have and is it open-weight yet? Qwen3.8 was announced on July 19, 2026 with up to 2.4 trillion parameters, described as launching and going open-weight soon, but at announcement time it remained a promise rather than a downloadable release. Qwen's earlier Qwen3 family, released under Apache 2.0, ranged from 0.6 billion to 32 billion dense parameters plus mixture-of-experts models up to 235 billion total parameters, with support in llama.cpp, Ollama, LM Studio, vLLM, and SGLang. _Developers tracking when frontier models actually become downloadable can follow releases like Qwen3.8 on daily.dev._ ## Community discussion Top comments from developers on daily.dev. **@harshitmanepally** · 6 upvotes > • Open-Weight AI: The final AI brain parameters are free to download and run locally, but the exact training dataset remains hidden. > > • Open-Source AI: The runtime code and weights are public, conforming to open licensing standards, but without full data transparency. > > • Open-Science AI: The absolute highest level of transparency where all weights, code, and exact datasets are shared for total scientific reproducibility. > > • Open-Data AI: A model built exclusively on completely public, unencumbered data, or an initiative that publicly shares its core training datasets. > > • Open-Architecture AI:... **@kartiknvj** · 0 upvotes > The ten-point checklist at the end is the part I'd bookmark, especially the reminder that tokenizer, config and inference code have to ship with the weights. I've pulled "open" checkpoints with a missing chat template and every eval number I ran was off until I found it. With Kimi K3 at 2.8 trillion parameters, I wonder how many people will ever run it outside a hosted provider. ## Similar posts on daily.dev - [A deep dive into open-weight AI models](https://daily.dev/posts/a-deep-dive-into-open-weight-ai-models-5r7yufmf3) · Flavio Copes · 0 upvotes · 0 comments - [What “Open Weight” Actually Means](https://daily.dev/posts/what-open-weight-actually-means-wlacoicak) · Medium · 0 upvotes · 0 comments - [“Don’t use ‘open weight’ and ‘open source’ interchangeably”: Percona CEO on why AI terminology matters](https://daily.dev/posts/don-t-use-open-weight-and-open-source-interchangeably-percona-ceo-on-why-ai-terminology-matte-f7uabgutc) · The New Stack · 0 upvotes · 0 comments - [Open Weights isn't Open Training](https://daily.dev/posts/open-weights-isn-t-open-training-r4hbjx8ei) · Hacker News · 1 upvotes · 0 comments - [Open Weights Is All You Need](https://daily.dev/posts/open-weights-is-all-you-need-8gjhbnwkm) · Kilo Blog · 1 upvotes · 0 comments --- Tags: [#open-source](https://daily.dev/tags/open-source), [#data-science](https://daily.dev/tags/data-science), [#llm](https://daily.dev/tags/llm), [#qwen](https://daily.dev/tags/qwen) [View this post on daily.dev](https://daily.dev/posts/what-open-weights-means-for-ai-models-6vljntk5i) ```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 “open weights” means for AI models","url":"https://daily.dev/posts/what-open-weights-means-for-ai-models-6vljntk5i","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/what-open-weights-means-for-ai-models-6vljntk5i"},"datePublished":"2026-10-14T10:22:25.732Z","dateModified":"2026-10-14T10:22:50.469Z","description":"Explains the difference between open weights, open access, and open-source AI, arguing that downloadable model parameters are not the same as a fully...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/f64a2b5e55122c5753bbc9eca3b5969b?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/f64a2b5e55122c5753bbc9eca3b5969b?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"Flavio Copes","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":"Flavio Copes","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/1f2dbd275797411bbd37bfdaaf0951a9","url":"https://daily.dev/sources/flaviocopes"},"commentCount":2,"discussionUrl":"https://daily.dev/posts/what-open-weights-means-for-ai-models-6vljntk5i","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":38},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":2}],"keywords":"open-source,data-science,llm,qwen","timeRequired":"PT13M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Flavio Copes","item":"https://daily.dev/sources/flaviocopes"},{"@type":"ListItem","position":3,"name":"What “open weights” means for AI models"}]} {"@context":"https://schema.org","@type":"WebPage","@id":"https://daily.dev/posts/what-open-weights-means-for-ai-models-6vljntk5i","comment":[{"@type":"Comment","text":"• Open-Weight AI: The final AI brain parameters are free to download and run locally, but the exact training dataset remains hidden.\n• Open-Source AI: The runtime code and weights are public, conforming to open licensing standards, but without full data transparency.\n• Open-Science AI: The absolute highest level of transparency where all weights, code, and exact datasets are shared for total scientific reproducibility.\n• Open-Data AI: A model built exclusively on completely public, unencumbered data, or an initiative that publicly shares its core training datasets.\n• Open-Architecture AI: The blueprint, mathematical layers, and structural design of the model are published openly, regardless of who owns the final trained weights.\nHope this helps!","datePublished":"2026-10-15T06:28:31.032Z","url":"https://daily.dev/posts/6vlJntk5i#c-4GCELJwkJ","author":{"@type":"Person","name":"HARSHIT MANEPALLY","url":"https://daily.dev/harshitmanepally","image":"https://media.daily.dev/image/upload/s--O0TOmw4y--/f_auto/v1715772965/public/noProfile"},"interactionStatistic":{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":6}},{"@type":"Comment","text":"The ten-point checklist at the end is the part I’d bookmark, especially the reminder that tokenizer, config and inference code have to ship with the weights. I’ve pulled “open” checkpoints with a missing chat template and every eval number I ran was off until I found it. With Kimi K3 at 2.8 trillion parameters, I wonder how many people will ever run it outside a hosted provider.","datePublished":"2026-10-15T19:38:02.181Z","url":"https://daily.dev/posts/6vlJntk5i#c-7FflO7bmK","author":{"@type":"Person","name":"kartik-nvjk","url":"https://daily.dev/kartiknvj","image":"https://media.daily.dev/image/upload/s--3gGgsVCw--/f_auto/v1781456774/avatars/avatar_TvTVeiMdkRCqWUDullFmy?_a=BAMAMiWQ0"}}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/what-open-weights-means-for-ai-models-6vljntk5i#faq","mainEntity":[{"@type":"Question","name":"What is the difference between open weights and open-source AI for a model?","acceptedAnswer":{"@type":"Answer","text":"Open weights means the trained parameters are downloadable so you can run, fine-tune, or quantize the model, but the training code, full dataset information, and reproducibility are not guaranteed. Open-source AI, per the Open Source Initiative's definition, requires weights plus the preferred materials needed to study and modify the system, including training code and enough data information to substantially recreate it. daily.dev readers weighing model licensing tradeoffs can dig into definitions like these before picking a model to deploy."}},{"@type":"Question","name":"How many parameters does Kimi K3 have and what is its architecture?","acceptedAnswer":{"@type":"Answer","text":"Kimi K3 has 2.8 trillion total parameters using a mixture-of-experts architecture with 896 experts, activating only 16 per token, which makes inference more efficient than using all parameters every time. It offers native vision and a 1-million-token context window. Moonshot AI announced it on July 16, 2026, and said full weights would release by July 27, 2026, recommending deployments with 64 or more accelerators. Teams sizing hardware for massive mixture-of-experts models can track releases like this one on daily.dev."}},{"@type":"Question","name":"How many parameters does Qwen3.8 have and is it open-weight yet?","acceptedAnswer":{"@type":"Answer","text":"Qwen3.8 was announced on July 19, 2026 with up to 2.4 trillion parameters, described as launching and going open-weight soon, but at announcement time it remained a promise rather than a downloadable release. Qwen's earlier Qwen3 family, released under Apache 2.0, ranged from 0.6 billion to 32 billion dense parameters plus mixture-of-experts models up to 235 billion total parameters, with support in llama.cpp, Ollama, LM Studio, vLLM, and SGLang. Developers tracking when frontier models actually become downloadable can follow releases like Qwen3.8 on daily.dev."}}]} ```