Prince Canuma
@Prince_Canuma • 22,524 subscribers
Apple MLX King 🤴🏽• Creator of (mlx-audio & mlx-vlm) • working on something new Ex-@arcee_ai • @neptune_ai • https://t.co/iZnxoefJBU
Shorts
Videos
Excited to introduce Nativ 🚀 Run frontier open models locally on your Mac. No accounts, no subscriptions, no cloud. ⚡ Built on mlx-vlm — multimodal + fastest on Apple Silicon 🔒 100% private — every token generated on your machine 🛠 Plug your coding agents into a local endpoint 📊 Live telemetry — tokens/sec, memory, usage 🆓 100% open source, MIT licensed, free forever Your Mac is more capable than you think. Stop renting intelligence. Download for macOS 👇 Github repo 🌟
Prince Canuma101,436 Aufrufe • vor 1 Tag
DeepSeek-V4-Flash powering 4 parallel agents on Pi (by Mario Zechner) 🚀 Running on M3 Ultra at ~30-34 tok/s and 160-187GB peak URAM using MLX-LM. Special shoutout to clandestine.eth 🦇🔊, Pedro Cuenca, Tarjei Mandt, Ivan Fioravanti ᯅ and others for helping optimize and shape this PR. PR:
Prince Canuma109,941 Aufrufe • vor 2 Monaten
Today we're shipping our biggest MLX-VLM release yet: v0.6.0 ...and we are raising 💸 This one's about turning your Apple devices into real local agent machines. From your desk to your pocket. What's new: ⚡ Speculative decoding everywhere — Gemma 4 EAGLE3 + DFlash, Qwen MTP, DeepSeek V4 MTP. Faster tokens, less waiting. 🤖 Agent-ready server — native Anthropic /v1/messages API, stateful /v1/responses, tool calls, Codex context budgets. Plug Claude Code & Codex straight into local models. 👁️ New models galore — DeepSeek V4, ZAYA1-VL, MiniCPM-V 4.6, LFM2 MoE, Step-3.7 Flash, Laguna + more. 🎨 Image gen & editing — FLUX.2 (base + klein), PrismML Bonsai. 🔊 Audio in — Qwen3 Omni, Gemma 4 audio, base64 chat audio. 🧮 TurboQuant KV cache — RHT-correct fast paths for leaner memory. 📦 Modular server, better metrics, cleaner streaming. Run real agents on the hardware already in your hands. Github:
Prince Canuma65,678 Aufrufe • vor 1 Monat
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 Lucas Newman and yours truly. iOS, macOS, and visionOS developers can now build native apps with real-time, on-device audio intelligence: 🗣️ Text-to-Speech (TTS) 👂 Speech-to-Text (STT) 🔄 Speech-to-Speech (STS) 🎙️ Voice Activity Detection (VAD) and more. Only import the capabilities you need, nothing extra. Get started today and leave us a star ⭐️
Prince Canuma160,927 Aufrufe • vor 4 Monaten
Congratulations to the Cohere team on the release of Cohere Transcribe Arabic! 🎉 Runs natively on mlx-audio (Python + Swift) from day-0 🚀 What's inside: → 2B params, Conformer encoder-decoder (audio-in, text-out) → Large Conformer encoder for acoustic representations + lightweight Transformer decoder for token generation → Built for Arabic dialects and Arabic-English code-switching → Auto-resampling to 16kHz + stereo→mono handling built into preprocessing → Apache 2.0 — fully open for community research Currently topping the Open Universal Arabic ASR Leaderboard 🥇 Get started today: 🐍 Python uv pip install -U mlx-audio 🍎 Swift
Prince Canuma16,454 Aufrufe • vor 14 Tagen
Next mlx-vlm release will ship with continuous batching support on the server 🚀 What's coming: → Continuous batching — new requests join the active batch immediately, no waiting. Mixed image + text batches supported → OpenAI-compatible API — field-for-field match with mlx-lm, reasoning/content split for thinking models, tag-aware streaming → Multi-turn tool calling — full tool use support across streaming and non-streaming, works with Gemma4 and other templates → Vision feature caching — cache image embeddings across turns. Gemma4: 228x speedup, Qwen3.5: 23x on cache hit All running locally on Apple Silicon. Check our this demo running 4 concurrent requests (mixed image + text) to gemma-4-26B-A4B-IT by Google Gemma in bf16 using Pi + MLX-VLM server on my M3 Ultra. One of the requests ingests a 8K resolution image!
Prince Canuma82,169 Aufrufe • vor 3 Monaten
Congratulations to the Cohere team on releasing North Mini Code 1.0 🔥 We provide day-0 support on MLX thanks to our close collaboration with the Cohere team. North Mini Code 1.0 is a 30B param MoE model with 3B active. It runs at ~66 tok/s in BF16, truly impressive speeds before any compression. Here is a quick demo I built using Pi by Mario Zechner & Armin Ronacher ⇌ as my agent hardness. Get started today: 1. Install mlx-vlm from source: > uv pip install git+ 2. Start the server and power your favourite agents (pi, opencode, hermes and etc) > uv run mlx_vlm.server --model CohereLabs/North-Mini-Code-1.0 New release tomorrow
Prince Canuma35,367 Aufrufe • vor 1 Monat
🎉 Congrats to MOSI + OpenMOSS on the release of MOSS-Transcribe-Diarize-0.9B — a genuinely impressive end-to-end ASR model for real-world, multi-speaker conversations. We're proud to partner with them for day-0 support on mlx-audio (Python & Swift). Now running local-first on Apple Silicon: 🎙️ transcript + speaker labels + timestamps in one pass 🗣️ unlimited-speaker diarization ⏱️ up to ~90 min of audio per input 🌍 90+ languages 🧠 128K context • Whisper-Medium encoder + Qwen3-0.6B decoder 🎯 hotword boosting for names, products & domain terms Perfect for meetings, podcasts, interviews, and long-form call analysis — no cloud, no data leaving your Mac. Get started now: 🐍 Python > uv pip install -U mlx-audio 🍎 Swift .package(url: " from: "0.1.3") Go build. 🚀
Prince Canuma11,369 Aufrufe • vor 12 Tagen
DeepSeek-v4 now runs at ~23-26 tok/s on MLX! I made some custom kernels for the sinkhorn and it took gen speeds for 17 -> 26 tok/s. The weights are also significantly smaller thanks to Pedro Cuenca tip about keeping the experts in MXFP4! Now you can use it to power your local coding agents (PI, Open code, Hermes agent or even CC) PR:
Prince Canuma58,451 Aufrufe • vor 2 Monaten
Local transcription running on iPad Pro M1 🔥 Qwen3-ASR-0.6B from Qwen — fully on-device, no cloud, no API calls. Built with our new MLX-Audio-Swift SDK, hitting 25 tok/s at just 1.9GB of RAM. Test audio? Found Marc Lou's old sales call from one of his awesome newsletters sitting on my device. Try it out & drop us a ⭐️
Prince Canuma81,427 Aufrufe • vor 5 Monaten
Marvis-TTS-v0.2 is here 🚀 A local first TTS model capable of realtime performance even on older iPhones that Lucas Newman and I built. What’s new: ✨ Blazing fast — 100M (tiny) & 250M parameter models 🌍 Multilingual — English, French, German 🎭 Enhanced voice cloning — More natural & expressive ⚡ Long-form generation — Up to 90 seconds (4x improvement) Get started today: > pip install -U mlx-audio
Prince Canuma118,352 Aufrufe • vor 8 Monaten
You can now vibecode your own WisprFlow or Monologue alternative that runs completely locally on Apple Silicon using MLX-Audio-Swift 🔥 Check out this live transcription of Dwarkesh Patel interview with Andrej Karpathy using Qwen3-ASR-0.6B quantized to 4bit on a M3 Max. It also runs in realtime on a iPhone 15 Pro and iPad Pro M1. No cloud. No API keys.
Prince Canuma60,974 Aufrufe • vor 4 Monaten
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 language support 🗣️Voice customization options 🚀Quantization support for optimized performance Supported models: 🪶Kokoro - A multilingual TTS model with 82M params that supports various languages and voice styles. With more models coming soon. Get started: > pip install mlx-audio Please leave us a star and send a PR :)
Prince Canuma123,480 Aufrufe • vor 1 Jahr
Introducing Marvis-TTS 🔥🚀 A new local-first TTS model Lucas Newman 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 real-time capabilities, Marvis flips the script. It streams audio chunks as text is processed, creating a truly conversational experience. No more awkward pauses or unnatural breaks—Marvis handles the entire text context intelligently to deliver coherent, expressive speech. Get started today: > pip install -U mlx-audio
Prince Canuma81,345 Aufrufe • vor 10 Monaten
RF-DETR by Roboflow now on MLX It can do realtime instance segmentation on-device and enable some cool use cases for visual analysis, monitoring and robotics like Reachy Mini. Also augmented VLM and VLA by preprocessing image and video with areas of interest. New release coming soon on mlx-vlm 🚀 For those who can’t wait you can install mlx-vlm from source.
Prince Canuma30,499 Aufrufe • vor 3 Monaten
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.
Prince Canuma56,286 Aufrufe • vor 8 Monaten
Introducing MLX-Audio Studio 🚀 An open-source UI for audio gen. This new UI will allow you to easily generate and transcribe audio locally using MLX-Audio, Transformers or any other backend you prefer (i.e. OpenAI). We will be adding more tasks soon, stay tuned! Get started on our GH:
Prince Canuma51,071 Aufrufe • vor 8 Monaten
🗓️ Release Week Recap Big week. mlx-audio and mlx-vlm are now among some of the fastest-growing OSS projects. Here’s what we shipped last week. Gemma 4 on Apple Silicon Two awesome releases by our partner Google DeepMind & Google Gemma : > Gemma 4 12B — their new dense, unified multimodal model. It uses an encoder free audio path and simplified vision encoder. > Gemma 4 QAT — quantization-aware training checkpoints, optimized to run locally on consumer GPUs and edge devices, compressing the model while preserving the quality you expect from Gemma 4. On the audio 🎧 side we added support for 15+ new TTS, ASR & VAD models, faster long-form transcription, and an expanded OpenAI-compatible audio server. All local on Apple Silicon. Huge thanks to every contributor and my co-maintainer Lucas Newman. 🙏🏽
Prince Canuma11,731 Aufrufe • vor 1 Monat