EXL3 is the biggest paradigm shift in local LLMs right now, and most people still have…
This is a dev post classified by Jev as Other (a tutorial), kept by the Dev Radar because it carries real work, not commentary.
EXL3 is the biggest paradigm shift in local LLMs right now, and most people still have not understood it. Not because it is new. Because everyone filed it as "another quant format" next to GGUF and AWQ, tried it once, and moved on. It is not another quant format. It is a different compression algorithm, and the difference compounds at every tier of hardware. I mapped every EXL3 implementation I could find, and the result is one lane per VRAM tier. Here is the best recipe for each tier, so you do not have to build it. WHY TRELLIS IS NOT JUST ANOTHER QUANT The formats you grew up on round ea
Posted by Yume_X (2.1k followers) 1 h ago · 4 likes · 166 views · view the original post on X. Kept by the Dev Radar as Other.
More dev work like this
- We're open-sourcing Asimov 1's locomotion policy and training code soon 🧡 — @asimovinc
- The clothes are waiting. One choice. One look. One transformation. — @PrunaAI
- Xiaomi's MiMo-V2.6 models are live on each::labs, day 0 🚀 — @eachlabs
- NVIDIA Isaac ROS 5.0 brings AI agents to robotics development. 🤖 — @NVIDIARobotics
- Xiaomi makes this 1500hp EV supercar that holds test track records in Germany, and has… — @hsu_steve
- 🎙️ Real-time interpretation, powered locally by VoxCPM2. — @OpenBMB
- saiitanaa released a Nintendo 3DS Homebrew app called CIATools, an all-in-one tool for… — @ReticentY2K
- Aging remains one of the most complex challenges in biological science. In a landmark… — @InSilicoMeds
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. 21k posts from 5k X accounts over the last 21 days, 2.4k tools, 12 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-22 14:50 UTC. Full method.