iiinova — where your digital self keeps evolving

Quixotic AI

@qxotic.ai

20 followers 19 following 8 posts

AI sovereignty for the world's most trusted runtime. qxotic.ai

Posts Replies Media

Reposted by Quixotic AI

jitLLM @jitllm.io · 16h

Can Java compete with llama.cpp/ollama? YES! With @jitllm.io! jitLLM uses NVIDIA CUDA features and libraries (cuBLAS, cuDNN) and reaches 0.90× to 1.12× of llama.cpp's throughput! jitLLM is empowered by @tornadovm.org and will be soon in @langchain4j.dev and @quarkus.io. github.com/beehive-lab/...

0104

Quixotic AI @qxotic.ai · 29/09/2026

"Write once, run anywhere!" Not "Write once, bridge to Python!" qxotic.ai#examples

022

Quixotic AI @qxotic.ai · 29/09/2026

AI 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...

051

Quixotic AI @qxotic.ai · 26/09/2026

Meet Tok'n'Roll 🎸 the tokenization substrate of qxotic.ai Token-perfect. Pure Java. Zero dependencies.

121

Quixotic AI @qxotic.ai · 25/09/2026

The JVM is a marvel of software engineering. AI on the JVM: quixotic ... until now. Local, fast, just one command away. qxotic.ai

122

Quixotic AI @qxotic.ai · 15/09/2026

Some would call AI on the JVM quixotic. We just shipped it. Chat, vision, embeddings & TTS on the JVM. Finally, AI in a jar. qxotic.ai

qxotic.ai

Quixotic AI: AI inference for the JVM at native speed

LLMs, vision, embeddings, and text-to-speech, all inside the JVM. AI in a jar.

050

Quixotic AI @qxotic.ai · 06/07/2026

Beep, beep! Early benchmarks of the Quixotic AI stack (JVM) vs. llama.cpp qxotic.ai

052