Prince Canuma (@Prince

Prince Canuma

23.3K posts

Prince Canuma

@Prince_Canuma

Apple MLX King 🤴🏽• Creator of (mlx-audio & mlx-vlm) • Ex-@arcee_ai • @neptune_ai • linktr.ee/prince.canuma

Krakow, Poland

github.com/Blaizzy

Born July 23

Joined July 2012

Pinned
Prince Canuma
@Prince_Canuma
Feb 23
Day 1 of 3 days of MLX: Introducing MLX-Audio-Swift SDK 🚀 A modular Swift SDK for voice agents and tasks on Apple Silicon built by @lllucas and yours truly. iOS, macOS, and visionOS developers can now build native apps with real-time, on-device audio intelligence: 🗣️
00:00
162K
Prince Canuma
@Prince_Canuma
Nov 9, 2025
1AM debugging session = 100% worth it ✅ Fixed critical Qwen3-VL bug in MLX-VLM with massive gains: Before: 10GB VRAM, 60.5 tok/s After: 5.5GB VRAM, 115 tok/s ~2x faster inference at half the memory footprint. Ship it 🚀
95K
Prince Canuma
@Prince_Canuma
Feb 28, 2025
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
00:00
124K
Prince Canuma
@Prince_Canuma
Nov 7, 2025
Marvis-TTS-v0.2 is here 🚀 A local first TTS model capable of realtime performance even on older iPhones that @lllucas and I built. What’s new: ✨ Blazing fast — 100M (tiny) & 250M parameter models 🌍 Multilingual — English, French, German 🎭 Enhanced voice cloning — More
00:00
118K
Prince Canuma
@Prince_Canuma
Oct 26, 2025
Deepseek OCR now on MLX :) Thanks for the patience! I finally found and fixed the bug on the LM part that was stopping it from understanding the Vision Tokens. New release later today, probably alongside batch infer to allow you to process N documents at once.
00:00
57K
Prince Canuma
@Prince_Canuma
Aug 26, 2025
Introducing Marvis-TTS 🔥🚀 A new local-first TTS model @lllucas and I built for efficiency, accessibility, and real-time performance right on consumer devices like Apple Silicon, iPhones, iPads, and more. Traditional TTS models often demand full text inputs or sacrifice
00:00
81K
Prince Canuma
@Prince_Canuma
Oct 21, 2025
Have said it before Qwen3-VL is one of the best OSS models for OCR
Maziyar PANAHI
@MaziyarPanahi
Oct 20, 2025
Qwen3 VL 4B doctor's hand written note!
43K
Prince Canuma
@Prince_Canuma
Dec 7, 2024
Llama 3.3 70B now on MLX You can run inference and finetune it locally on your Mac. > pip install -U fastmlx mlx-lm
Llama 3.3 - a mlx-community Collection
From huggingface.co
32K
Prince Canuma
@Prince_Canuma
Aug 5, 2025
Coming to MLX
Sam Altman
@sama
Aug 5, 2025
gpt-oss is out! we made an open model that performs at the level of o4-mini and runs on a high-end laptop (WTF!!) (and a smaller one that runs on a phone). super proud of the team; big triumph of technology.
37K
Prince Canuma
@Prince_Canuma
May 11, 2025
MLX-Audio v0.2.0 is here! And it’s our biggest update yet 🚀 What’s new: Speech-to-Speech 💬 - We now have modular STS pipeline. You can speak with your computer by mixing and matching your favourite STT, LM (VLM soon) and TTS models. Yes, you can interrupt it :) MLX-Audio
29K
Prince Canuma
@Prince_Canuma
Oct 20, 2025
Coming to MLX 🚀
deepseek-ai/DeepSeek-OCR at main
From huggingface.co
24K
Prince Canuma
@Prince_Canuma
Dec 24, 2024
QvQ-72B-Preview now on MLX 🚀🎄 TLDR 🏆SoTA open-source multimodal 🧠 Capable of step-by-step reasoning 💪🏾 Competitive MMMU score with o1, GPT-4o and Sonnet 3.5 🔥 Beats GPT-4o and Sonnet 3.5 on MathVista and MathVision You can now run inference and finetune (QLora) locally on
00:00
Qwen
@Alibaba_Qwen
Dec 24, 2024
🎄Happy holidays and we wish you enjoy this year. Before moving to 2025, Qwen has the last gift for you, which is QVQ! 🎉 This may be the first open-weight model for visual reasoning. It is called QVQ, where V stands for vision. It just reads an image and an instruction, starts
57K
Prince Canuma
@Prince_Canuma
Oct 16, 2025
I got engaged and married to the love of my life ❤️ After being abroad since 2017, working hard to become a better man, God blessed me 3 years ago with someone truly special. Last September, I flew to Zimbabwe 🇿🇼 to marry (traditionally) this wonderful, smart, and beautiful
25K
Prince Canuma
@Prince_Canuma
May 30, 2025
Thank you very much @OpenAI for the amazing Swag! Looking forward to your first open model and the MLX Port!🔥🚀
27K