oMLX 0.7.0.dev4 adds DeepSeek V4.1 CED prefill with up to 79% faster prompt processing…
This is a AI post classified by Jev as Open & local models (a launch), kept by the AI Radar because it carries real work, not commentary.
oMLX 0.7.0.dev4 adds DeepSeek V4.1 CED prefill with up to 79% faster prompt processing on M3 Ultra (opt-in), multi-request Lightning MTP, and plenty of quality-of-life improvements including one-click model settings. https://github.com/jundot/omlx/releases/tag/v0.7.0.dev4 You can now apply model settings with one click using over 450,000 community benchmarks on https://omlx.ai. Pick a top result for your Mac chip and model to use the same settings. Using a customized model? Copy a one-line recipe from a model with the same architecture and paste it into oMLX. There's also a customizable dashb
Posted by Jun Kim (2.7k followers) 2 days ago · 106 likes · 4.3k views · view the original post on X. Kept by the AI Radar as Open & local models. Tools mentioned: omlx, Community Benchmarks.
More AI work like this
- Yes we are a healthcare company. Yes we just released the best open-weight alternative… — @4rcherhume
- Qwen又发大招了，Qwen-Image-2.1开源了，这是一个7B参数的文生图模型，对本地图像生成模型部署具有史诗级意义 — @xueyu1125
- Pirate Face activity · 21 Sept 2026 — @thepirateface
- Qwen-image-2.1 running on one of my DGX Sparks — @MichaelGannotti
- Qwen 2.1 Image Reference 2 Image is SOLID — @Tech2Wild
- One day after Laya and 4 after Jev, @cognition releases Kev another open model that… — @plotarmordev
- Many things in the Local / Self-hosted AI comes down to "skill issue" — @TheAhmadOsman
- My Bonzai 2 27B Ablitrated is getting a fair number of downloads! I'd love to hear what… — @Hikari_07_jp
Every post is read and classified by Jev (TypeSafe): what it is, which market it belongs to, and whether the link is a real tool. 38k posts from 4.9k X accounts over the last 14 days, 1.6k tools, 19 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-21 07:04 UTC. Full method.