Prince Canuma
@Prince_Canuma
Apple MLX King 🤴🏽• ML Research Engineer👨🏾💻 • VLMs • LLMs • Speaker • Writer • Ex-@arcee_ai • @neptune_ai • https://linktr.ee/prince.canuma
Day 1 of 3 MLX Releases: Introducing MLX-Audio 🚀🔥 A text-to-speech (TTS) and Speech-to-Speech (STS) library built on Apple's MLX framework, providing efficient speech synthesis on Apple Silicon. Features ⚡️Fast inference on Apple Silicon (M series chips) 🤖Multiple…
Give me the $93M and I will pour it all into MLX, LlamaCPP and developing the best local AI tooling ever 😎🔥
>AI THERAPY APP >A16Z >$93 MILLION I tried this atrocity Vibe coded all the way down It’s like talking to GPT-1 And it takes a full business day and $250 in compute to get a response BURN IT ALL DOWN PONZI ESCAPE VELOCITY ACHIEVED *sponsored by -99999% gross margins
Thank God for another awesome year full of blessings, increase and connections! 🎉🎂 And you thank you @CxMahachi for the delicious Pancakes ❤️
Those 512GB look very attractive now
Bye Qwen3-235B-A22B, hello Qwen3-235B-A22B-2507! After talking with the community and thinking it through, we decided to stop using hybrid thinking mode. Instead, we’ll train Instruct and Thinking models separately so we can get the best quality possible. Today, we’re releasing…
Qwen3 coder now on MLX! 🚀🔥
A perfect coding model for MLX on Apple silicon.. Qwen delivered again. Runs quite fast on an M3 Ultra. Running the 4-bit quantized with mlx-lm:
Woohoo
this is what is not small! boys spent so much time building the Qwen3-Coder after Qwen2.5-Coder. it is much bigger, but based on MoE, and way stronger and smarter than before! not sure we can say competitive with claude sonnet 4 but might be for sure a really good coding agent.…
This is crazy 😂
🚨BREAKING: META JUST POACHED 3 GOOGLE DEEPMIND RESEARCHERS WHO BUILT IMO GOLD MEDAL MODEL The Zucc cannot be stopped.
1 or 2 Maxed M3 Ultra should do it 👌🏽
We're gonna need a bigger GPU
Where have I seen this before? 🤔
Introducing Anti-Clueless by Nodes The first full-stack AI talent acquisition platform that automates the entire hiring process — from sourcing, headhunting, screening, to retention
Let me see if I get Silicon Valley: Top engineer -> circulate in FAANG Courageous top engineer -> Fork OSS or use API (startup) -> if lucky (acquired by FAANG)
I know the feeling
I need my M3 Ultra The Beast back online asap! 🔥🔥🔥
The MLX community is truly amazing ❤️ “Ask, and it will be given to you; seek, and you will find; knock, and it will be opened to you.” — Matthew 7:7-8
The beast is on the way! 🚀🙌🏽
The beast is on the way! 🚀🙌🏽
Guys it's time to help your MLX King ♥️ If love my work, please sponsor me :) The goal is to raise $13K for a maxed out M3 Ultra to port larger models for the community. Sponsor Link: github.com/sponsors/Blaiz…
Tomorrow is my birthday and my house is an absolute Sherlock Holmes’s puzzle 🤣🙌🏽
Crazy part majority of my younger siblings are now an adults And although the first, I’m now officially the shortest son. They all got my grandfather’s height (+1.80m)
I left home in 2017 and haven’t been back since 😅 Can’t wait to see everyone again soon!
I left home in 2017 and haven’t been back since 😅 Can’t wait to see everyone again soon!
LFG!
time to reproduce Kimi K2's agentic data synthesis pipeline in the open