<!-- mobian-agent-page publisher="dailydev" canonical="https://daily.dev/posts/adam-bien-s-blog-07esknjrq" -->

---
title: adam bien&#x27;s blog | daily.dev
description: lightmetal is a single Java 25 executable JAR that runs GPU-accelerated LLM inference on Apple Silicon with zero dependencies. It binds a Metal-enabled...
canonical: https://daily.dev/posts/adam-bien-s-blog-07esknjrq
twitter:card: summary_large_image
twitter:site: @dailydotdev
og:type: website
og:site_name: daily.dev
og:title: adam bien&#x27;s blog | daily.dev
og:description: lightmetal is a single Java 25 executable JAR that runs GPU-accelerated LLM inference on Apple Silicon with zero dependencies. It binds a Metal-enabled...
og:url: https://daily.dev/posts/adam-bien-s-blog-07esknjrq
og:image: https://api.daily.dev/og/posts/07eSKnJrq.png
og:image:alt: adam bien&#x27;s blog
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.

# adam bien's blog

**[Adam Bien](https://daily.dev/sources/adam-bien)** · 1 min read · 0 upvotes · 0 comments

## Summary

lightmetal is a single Java 25 executable JAR that runs GPU-accelerated LLM inference on Apple Silicon with zero dependencies. It binds a Metal-enabled libllama.dylib via the Foreign Function & Memory API (FFM) and supports Mistral and Gemma GGUF models locally. The JAR can run as a CLI tool, expose OpenAI- and Anthropic-compatible HTTP endpoints with a -serve flag, or be embedded into other Java apps via ServiceLoader with no compile-time dependency. No Python, no Ollama, no containers required.

## Full article

daily.dev links to this article rather than hosting it. Read it at the original source: <https://adambien.blog/roller/abien/entry/lightmetal_gpu_llm_inference_from_a_single_java_25_jar>

## Similar posts on daily.dev

- [adam bien's blog](https://daily.dev/posts/adam-bien-s-blog-autb4g2p8) · Adam Bien · 0 upvotes · 0 comments
- [Reach native speed with MacOS llama.cpp container inference](https://daily.dev/posts/reach-native-speed-with-macos-llama-cpp-container-inference-80y2u71zu) · Red Hat Developer · 0 upvotes · 0 comments

---

Tags: [#java](https://daily.dev/tags/java), [#ai-inference](https://daily.dev/tags/ai-inference)

[View this post on daily.dev](https://daily.dev/posts/adam-bien-s-blog-07esknjrq)

```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":"adam bien's blog","url":"https://daily.dev/posts/adam-bien-s-blog-07esknjrq","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/adam-bien-s-blog-07esknjrq"},"datePublished":"2026-06-09T06:56:36.169Z","dateModified":"2026-06-09T06:56:56.572Z","description":"lightmetal is a single Java 25 executable JAR that runs GPU-accelerated LLM inference on Apple Silicon with zero dependencies. It binds a Metal-enabled...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/d365e8cabb5d95ba36aaa092c23f211d?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/d365e8cabb5d95ba36aaa092c23f211d?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"Adam Bien","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":"Adam Bien","logo":"https://media.daily.dev/image/upload/s--CInnAL-q--/f_auto,q_auto/v1773644276/logos/adam-bien?_a=BAMAMiiu0","url":"https://daily.dev/sources/adam-bien"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/adam-bien-s-blog-07esknjrq","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"java,ai-inference","timeRequired":"PT1M"}
{"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Adam Bien","item":"https://daily.dev/sources/adam-bien"},{"@type":"ListItem","position":3,"name":"adam bien's blog"}]}
```

