--- title: I'm running a 284-billion-parameter model locally, and... description: DeepSeek V4 Flash, a 284-billion-parameter mixture-of-experts model, can be run locally on a 128GB machine using ds4, a purpose-built inference engine written... canonical: https://daily.dev/posts/i-m-running-a-284-billion-parameter-model-locally-and-it-competes-with-cloud-ai-vukpiym14 twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: I'm running a 284-billion-parameter model locally, and it competes with cloud AI | daily.dev og:description: DeepSeek V4 Flash, a 284-billion-parameter mixture-of-experts model, can be run locally on a 128GB machine using ds4, a purpose-built inference engine written... og:url: https://daily.dev/posts/i-m-running-a-284-billion-parameter-model-locally-and-it-competes-with-cloud-ai-vukpiym14 og:image: https://api.daily.dev/og/posts/Vukpiym14.png og:image:alt: I'm running a 284-billion-parameter model locally, and it competes with cloud 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. # I'm running a 284-billion-parameter model locally, and it competes with cloud AI **[XDA Developers](https://daily.dev/sources/xda-developers)** · 12 min read · 0 upvotes · 0 comments ## Summary DeepSeek V4 Flash, a 284-billion-parameter mixture-of-experts model, can be run locally on a 128GB machine using ds4, a purpose-built inference engine written by Redis creator Salvatore Sanfilippo. Unlike general-purpose runners like Ollama or llama.cpp, ds4 is hand-tuned exclusively for DeepSeek V4, using aggressive mixed-precision quantization (2-bit for routed expert layers, higher precision for shared components) to preserve tool-calling accuracy. A key innovation is persisting the KV cache to SSD, turning large context windows from a memory wall into a disk-space question and enabling session resumption without reprocessing. On a Lenovo ThinkStation PGX (GB10 Grace Blackwell, 128GB unified memory), generation runs at 10–14 tokens/second, slowing further with large contexts. The setup is best suited for long, unattended agentic tasks — overnight code refactors, codebase documentation — where privacy, zero API costs, and local execution matter more than speed. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Similar posts on daily.dev - [GitHub - antirez/ds4: DeepSeek 4 Flash local inference engine for Metal](https://daily.dev/posts/github---antirez-ds4-deepseek-4-flash-local-inference-engine-for-metal-sqcj9sya5) · Hacker News · 3 upvotes · 0 comments - [DeepSeek-V4.1-Flash on vLLM: 5x Agentic Throughput Since Day 0](https://daily.dev/posts/deepseek-v4-1-flash-on-vllm-5x-agentic-throughput-since-day-0-js5lna7tm) · vLLM · 0 upvotes · 0 comments - [DeepSeek-V4: a million-token context that agents can actually use](https://daily.dev/posts/deepseek-v4-a-million-token-context-that-agents-can-actually-use-uczd4kivx) · Hugging Face · 27 upvotes · 2 comments --- Tags: [#data-science](https://daily.dev/tags/data-science), [#local-ai](https://daily.dev/tags/local-ai), [#deepseek](https://daily.dev/tags/deepseek), [#mixture-of-experts](https://daily.dev/tags/mixture-of-experts) [View this post on daily.dev](https://daily.dev/posts/i-m-running-a-284-billion-parameter-model-locally-and-it-competes-with-cloud-ai-vukpiym14) ```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":"I'm running a 284-billion-parameter model locally, and it competes with cloud AI","url":"https://daily.dev/posts/i-m-running-a-284-billion-parameter-model-locally-and-it-competes-with-cloud-ai-vukpiym14","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/i-m-running-a-284-billion-parameter-model-locally-and-it-competes-with-cloud-ai-vukpiym14"},"datePublished":"2026-07-18T17:02:07.018Z","dateModified":"2026-07-23T23:56:35.722Z","description":"DeepSeek V4 Flash, a 284-billion-parameter mixture-of-experts model, can be run locally on a 128GB machine using ds4, a purpose-built inference engine written...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/f422d8151f489792e6668d05bee4047a?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/f422d8151f489792e6668d05bee4047a?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"XDA Developers","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":"XDA Developers","logo":"https://media.daily.dev/image/upload/s--kCg6yyAP--/f_auto,q_auto/v1774964407/logos/xda-developers?_a=BAMAMiWQ0","url":"https://daily.dev/sources/xda-developers"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/i-m-running-a-284-billion-parameter-model-locally-and-it-competes-with-cloud-ai-vukpiym14","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"data-science,local-ai,deepseek,mixture-of-experts","timeRequired":"PT12M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"XDA Developers","item":"https://daily.dev/sources/xda-developers"},{"@type":"ListItem","position":3,"name":"I'm running a 284-billion-parameter model locally, and it competes with cloud AI"}]} ```