Hackernews posts about MLX

1. Fastest LLM decode engine on Apple Silicon. 658 tok/s on M4-max,beats mlx by 19% (www.runanywhere.ai)
   5 points by sanchitmonga22 14 days ago | 3 comments
2. Full speech pipeline in native Swift/MLX – ASR, TTS, speech-to-speech, on-device (github.com)
   5 points by ipotapov 18 days ago | 2 comments
3. Show HN: EdgeWhisper – On-device voice-to-text for macOS (Voxtral 4B via MLX) (edgewhisper.com)
   3 points by raphaelmansuy 7 days ago | 1 comments
4. vLLM-mlx – 65 tok/s LLM inference on Mac with tool calling and prompt caching (github.com)
   3 points by raullen 23 days ago | 1 comments
5. Mlx-ONNX: Run your MLX models in the browser using WebGPU (github.com)
   3 points by skryl 24 days ago | 1 comments
6. Semantic grep running locally on Apple Silicon via MLX (github.com)
   3 points by car 22 days ago | discuss
7. MLX: Basics (ml-explore.github.io)
   2 points by tosh 7 days ago | discuss
8. OpenFelix – Open-source AI assistant for macOS (local MLX and any cloud model) (github.com)
   2 points by openfelixai 15 days ago | discuss
9. Show HN: Local TTS for OpenClaw on Apple Silicon (MLX-Powered, Zero Setup) (github.com)
   2 points by ZacharyZZ 29 days ago | discuss
10. Jax Metal vs. MLX (ndalton12.github.io)
    1 points by tosh 2 days ago | discuss
11. MLX: CUDA (ml-explore.github.io)
    1 points by tosh 6 days ago | discuss
12. Show HN: Courtyard – Open-source macOS app for local MLX fine-tuning Text (github.com)
    1 points by tuwenbo0120 24 days ago | discuss
13. Launch HN: RunAnywhere (YC W26) – Faster AI Inference on Apple Silicon (github.com)
    240 points by sanchitmonga22 11 days ago | 153 comments
14. Show HN: Open dataset of real-world LLM performance on Apple Silicon (devpadapp.com)
    2 points by uncSoft 16 days ago | 4 comments
15. LotusQ Cross platform voice dictation with free local Whisper(Mac/Windows/Linux)
    2 points by nkodev 17 days ago | 2 comments
16. Show HN: Llamactl – Self-hosted LLM manager with OpenAI-compatible routing (github.com)
    2 points by lordmathis 4 days ago | discuss
17. Show HN: Build a $10 AI Toy that runs locally on your Mac (github.com)
    2 points by akadeb 5 days ago | discuss
18. Show HN: I built a unified inference layer for Document Processing Models (github.com)
    2 points by Adithya-Kolavi 24 days ago | discuss
19. Show HN: AI Toys that don't need the internet (github.com)
    1 points by akadeb 6 days ago | discuss
20. Show HN: Familiar – Open-source local AI agent for macOS(and iOS) (thoughts.jock.pl)
    1 points by joozio 11 days ago | discuss
21. Show HN: 100% local speech dictation app with wakeword detection (mohdali7.gumroad.com)
    1 points by computerex 16 days ago | discuss
22. Nvidia PersonaPlex 7B on Apple Silicon: Full-Duplex Speech-to-Speech in Swift (blog.ivan.digital)
    374 points by ipotapov 16 days ago | 125 comments
23. Show HN: I fine-tuned Qwen 3.5 (0.8B–4B) on a Mac for text-to-SQL – 2B beats 12B (github.com)
    7 points by sciences44 16 days ago | 1 comments
24. I Don't Know ML. Claude Does. 0.871 F1 on Predicting Linux Game Compatibility (getjump.me)
    4 points by GetJump 3 days ago | 1 comments
25. Migrating Elderly Care AI from Qwen 3 to 3.5 on Apple Silicon – 14x Latency Fix (medium.com)
    2 points by asqpl 18 days ago | 1 comments
26. MacBook Pro with M5 Pro and M5 Max (www.apple.com)
    862 points by scrlk 18 days ago | 979 comments
27. Get free Claude max 20x for open-source maintainers (claude.com)
    580 points by zhisme 22 days ago | 235 comments
28. AirPods Max 2 (www.apple.com)
    321 points by ssijak 5 days ago | 557 comments
29. In 1985 Maxell built a bunch of life-size robots for its bad floppy ad (buttondown.com)
    142 points by rfarley04 17 days ago | 23 comments
30. Running a One Trillion-Parameter LLM Locally on AMD Ryzen AI Max+ Cluster (www.amd.com)
    75 points by mindcrime 20 days ago | 25 comments