←
Alfonso² Peterssen156 posts
Alfonso² Peterssen avatar

Alfonso² Peterssen

@TheMukel

"AI in a jar" @ Quixotic AI

◷ Joined August 2015▧ 4 Photos and videos
Fabio Niephaus avatar
⟳ Alfonso² Peterssen retweeted
Fabio Niephaus@fniephaus·Oct 14

The next generation of @GraalVM is shaping up nicely: fast startup, low CPU and memory usage, with no build step or project changes required! 🚀 Here’s a simple benchmark using a single-file program:

Post attachment
Quixotic AI avatar
⟳ Alfonso² Peterssen retweeted
Quixotic AI@qxoticai·Oct 13

Spring Boot shops, banks, insurers, payroll systems, all the backends that quietly run the world: millions of JVM apps can now add a 24B-A2B reasoning model as a plain Maven dependency. Every Liquid AI model is supported. No infra. No ops. No Python. 1009 tok/s prefill (~2.3x llama.cpp) 47.8 tok/s decode (parity) qxotic.ai

Today we release 𝙻𝙵𝙼𝟸.𝟻-𝟸𝟺𝙱-𝙰𝟸𝙱, the largest 𝙻𝙵𝙼𝟸.𝟻 family member. It is an efficient local model for laptops and PCs to work through multi-step tasks inside popular agent harnesses. > 24B total parameters, 2B active per token > Context expanded to 131K tokens > A 128K-token vocabulary > 33T pretraining tokens > It is a reasoning model > Very easy to fine-tune and customize > Performs competitively with Qwen3.6-35B-A3B, a model with ~50% more total and active parameters, on agentic and tool-use tasks. > Open base and post-trained weights on @huggingface 🤗 1/

Post attachment
Graeme Rocher avatar
⟳ Alfonso² Peterssen retweeted
Graeme Rocher@graemerocher·Oct 5

Think we should consider renaming Micronaut Framework to Micronaut Intelligence Cache AI edition 😎

Stéphane Épardaud avatar
⟳ Alfonso² Peterssen retweeted
Stéphane Épardaud@UnFroMage·Oct 1

I can't be the only one thinking @maxandersen deserves a Hall Of Fame award for single handedly making Java CLIs usable/viable with @jbangdev. It's such a massive lever and key to the story.

Quixotic AI avatar
⟳ Alfonso² Peterssen retweeted
Quixotic AI@qxoticai·Sep 29

AI in Java, at native speed, competitive with native engines on CPUs. qxotic.ai/#benchmarks

AI in Java... quixotic, until now! End-to-end AI stack for the JVM, built from first principles: Tokenizers, quantized matrix multiplication, model format readers, inference engine, vision, speech: all in Java. No external services, no wrappers, no Python, no ONNX. Will be presented at Devoxx Belgium, next week: "Quixotic: Pure Java Inference at Native Speed" m.devoxx.com/events/dvbe26/t…

Post attachment
Quixotic AI avatar
⟳ Alfonso² Peterssen retweeted
Quixotic AI@qxoticai·Sep 26

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

Post attachment