Coming soon, more ways to run Deepseek sub 128GB Ram on MLX-Serve.
This is a dev post classified by AGK Intelligence as Hosting & infra (a launch), kept by the Dev Radar because it carries real work, not commentary.
Coming soon, more ways to run Deepseek sub 128GB Ram on MLX-Serve. Honestly this model is so good, at 96 - 128GB, It should be everyone’s new default. Upcoming pruned iQ-MLX DS4 pack will run on a 96GB M5U with ioGPU set to 90, it will be tight, but fully in memory. And... hoping for a Qwen's release soon, and it will make this post obsolete 🤞
Posted by David Dalcu (3.1k followers) 2 h ago · 43 likes · 1.2k views · view the original post on X. Kept by the Dev Radar as Hosting & infra.
More dev work like this
- Introduction to Docker by Bobby Iliev (2024) is now in @ChapterPal's collection of open… — @burkov
- Phaze CEO @boxerbk explains why AI agents shouldn't have to take over your computer to… — @MTSlive
- We recently announced Workload Identity support for self-managed Kubernetes clusters in… — @OracleDevs
- GPT 6.2 Astra & 6.2 Sol have been deployed on Google Cloud — @lyraxana
- do people organically recommend https://boat.dev's cloud VMs for agent fleets online now? — @AniC_dev
- looking for errored out https://boat.dev VMs to repair — @AniC_dev
- AI factories need a unified way to manage infrastructure at scale. — @NVIDIAAIInfra
- R2 bucket metrics now break down request activity by region and errors by HTTP status… — @Jilles
Every post is read and classified by AGK Intelligence: what it is, which market it belongs to, and whether the link is a real tool. 31.6k posts from 5k X accounts over the last 21 days, 9.3k tools, 12 markets. New posts are collected several times an hour and the full ranking is recomputed every hour — last update 2026-11-05 05:27 UTC. Full method.