Reposted by Alfonso² PeterssenQuixotic AI @qxotic.ai · 29/09/2026"Write once, run anywhere!" Not "Write once, bridge to Python!" qxotic.ai#examples 022
Alfonso² Peterssen @mukel.bsky.social · 29/09/2026AI in Java, at native speed, competitive with native engines on CPUs. qxotic.ai#benchmarksqxotic.aiQuixotic AI: AI inference for the JVM at native speedLLMs, vision, embeddings, and text-to-speech, all inside the JVM. AI in a jar. 020
Reposted by Alfonso² PeterssenQuixotic AI @qxotic.ai · 29/09/2026AI in Java... quixotic, until now! End-to-end AI stack for the JVM, built from first principles. Will be presented at Devoxx Belgium, next week: "Quixotic: Pure Java Inference at Native Speed" m.devoxx.com/ev m.devoxx.com/events/dvbe2... 041
Reposted by Alfonso² PeterssenQuixotic AI @qxotic.ai · 26/09/2026Meet Tok'n'Roll 🎸 the tokenization substrate of qxotic.ai Token-perfect. Pure Java. Zero dependencies. 121
Reposted by Alfonso² PeterssenQuixotic AI @qxotic.ai · 25/09/2026The JVM is a marvel of software engineering. AI on the JVM: quixotic ... until now. Local, fast, just one command away. qxotic.ai 122
Reposted by Alfonso² PeterssenBenoit Daloze @eregon.me · 17/09/2026TruffleRuby runs Doom at, 🥁, 662 FPS! From the talk of @khasinski.bsky.social at #EuRuKo 1122
Reposted by Alfonso² PeterssenQuixotic AI @qxotic.ai · 06/07/2026Beep, beep! Early benchmarks of the Quixotic AI stack (JVM) vs. llama.cpp qxotic.ai 052
Reposted by Alfonso² PeterssenDevoxx Belgium @devoxx.com · 09/04/2026🚀 Gemma4 Java runner: • Single file, no deps • E2B→31B + MoE • GGUF + quant (F16→Q8) • Vector API ⚡ • CLI + thinking modes • GraalVM native + instant TTFT Pure Java 😏 by @mukel.bsky.social github.com/mukel/gemma4...github.com 173
Alfonso² Peterssen @mukel.bsky.social · 07/04/2026Strong with the JVM, Gemma 4 is 😌 jbang gemma4@mukel \ --model %{https://hf.co/unsloth/gemma-4-E2B-it-GGUF/resolve/main/gemma-4-E2B-it-Q8_0.gguf} \ --system-prompt "like Master Yoda, reply you must" \ --chat ~5GB once, download you must. Python or CUDA, you need not. Local AI, this is. 142
Alfonso² Peterssen @mukel.bsky.social · 07/04/2026Over the Easter weekend, I got Gemma 4 running in pure Java. No Python. No JNI. No native code. Just the JVM. github.com/mukel/gemma4...github.com 041
Reposted by Alfonso² PeterssenAlina Yurenko @alina-yurenko.bsky.social · 08/10/2025My @graalvm.org Native Image deep dive recording is already up: youtube.com/watch?v=1J6m... 🐰🚀 It includes the very public first demo of Project Crema, Open World for Native Image, at 2:19:54 😅 Thank you, @devoxx.com! All demos and notes are here: github.com/alina-yur/gr...youtube.comDeep Dive: GraalVM in Practice by Alina YurenkoYouTube video by Devoxx 0237
Reposted by Alfonso² PeterssenJosh Long 🍃 @starbuxman.joshlong.com · 16/04/2025run an LLM with a supercharged engine powered by Java and GraalVM (ht @alina-yurenko.bsky.social ) www.youtube.com/shorts/7zSEa...youtube.comRun a supercharged LLM powered by Java and GraalVM #ai #programming #javaprogramming #java #graalvmYouTube video by Coffee + Software 0173
Reposted by Alfonso² PeterssenAlina Yurenko @alina-yurenko.bsky.social · 16/04/2025✅ @graalvm.org Native Image ✅ Llama3.java ✅ Vector API, FFM API ✅ Apple Silicon ❤️ — `git clone github.com/mukel/llama3... ` — `sdk install java 25.ea.17-graal` — `make native` (optionally preload a model for zero overhead) — Profit!🚀 #Java #GraalVM #LLM #LLama 0319
Reposted by Alfonso² PeterssenChristian Humer @chumer.dev · 16/02/2025I had lots of fun talking about my early days as a dev, how I caused double credit bookings all over Germany, stopped smoking to survive long GraalVM meetings and how to heat the room with Java inception. Already looking forward to part 2. 1187
Reposted by Alfonso² PeterssenAlina Yurenko @alina-yurenko.bsky.social · 15/01/2025what's new in llama3.java and the upcoming @graalvm.org for JDK 24 🔥 Try it out here: github.com/mukel/llama3... @stephanjanssen.be @mukel.bsky.social #VDCERN #VoxxedDaysCERN 1235
Reposted by Alfonso² PeterssenChristian Humer @chumer.dev · 20/12/2024This will be a big deal 🪄🤩. Normally the debug experience of natively compiled languages get obfuscated due to compiler optimisations like inlining. Not here. All optimizations can be enabled to debug GraalVM native images and it looks just the same as without opts. 1122
Reposted by Alfonso² PeterssenFabio Niephaus @fniephaus.com · 20/12/2024We just merged the current status of the upcoming JDWP support for @graalvm.org Native Image! 🥳 This will soon provide developers with the same debugging experience they are used to in Java, but for native images! Stay tuned for more details. github.com/oracle/graal... 35526
Reposted by Alfonso² PeterssenStephan Janssen @stephanjanssen.be · 25/11/2024Excited to welcome @mukel.bsky.social as my co-speaker for the VoxxedDays #CERN talk on "The Era of AAP: Ai Augmented Programming using only Java" ☕️ 🚀 🔥 cern.voxxeddays.com/talk/the-era... 0153
Alfonso² Peterssen @mukel.bsky.social · 16/11/2024buff.ly/40KmT0t Graal compiler: +10% faster inference with the latest early access build. New features: batched prompt processing & AVX512 support.buff.lyGitHub - mukel/llama3.java: Practical Llama 3 inference in JavaPractical Llama 3 inference in Java. Contribute to mukel/llama3.java development by creating an account on GitHub. 02813
