← Latest products

Jinfer

AI inference engine for the JVM. AI in a jar. Run LLMs, vision, embeddings, and text-to-speech on the JVM at native speed. No Python runtime, ONNX bridges, or Docker sidecars. And so, Quixotic AI was born.

Visit qxotic.aiexternal site

Reactions (1)

Similar products

by description similarity

  1. 50+ LLMs on 2 GPUs with 2-Second Swapping? We built AI-Native Runtime

    github.com

    InferX: Inference as a Service Platform

    Hacker News5 pts

  2. We made our own inference engine for Apple Silicon

    github.com

    A high-performance inference engine for AI models

    Hacker News186 pts

  3. Low-latency local LLM runner via OpenJDK Panama FFM (Java 22)

    github.com

    Unified native AI runtime for Java 17+, Java 22+ (Panama FFM), Android & C++. Run GGUF LLMs, Vision, Video, Whisper ASR, TTS & Embeddings in-process.

    Hacker News38 pts

  4. Jlama

    github.com

    A fast Java inference engine for GPT and Llama models

    Hacker News7 pts

  5. Marvin

    github.com

    build AI functions that use an LLM as a runtime

    Hacker News127 pts