✅ BENCHMARKED: @NaceAI's Drex Max open-weight model makes decisions in under a second on…
This is a AI post classified by AGK Intelligence as Open & local models (a model release), kept by the AI Radar because it carries real work, not commentary.
✅ BENCHMARKED: @NaceAI's Drex Max open-weight model makes decisions in under a second on my 64GB M5 Pro Mac mini, running on their own Kapitsa runtime. Nace just published a technical report on how these decision models are trained. I ran the open Drex Max v1 weights locally to see what that looks like on a Mac. They released Drex Max as an open-weight decision model, plus Kapitsa, a runtime for Macs. Instead of generating a response token by token, Drex Max takes a prompt (say, a document and the possible decisions) and one forward pass returns a probability for each decision. I ran the of
Posted by Pratik Gandhi (12.6k followers) 1 h ago · 16 likes · 598 views · view the original post on X. Kept by the AI Radar as Open & local models. Tools mentioned: Console by Nace.AI.
More AI work like this
- 💥炸了！本地跑Qwen 3.8新巅峰！tqLLM 1.4.4碾压TensorFold/Strata/Splash，27B & Flash-Next速度起飞，Qwen… — @NFT_Chen
- Meet Arete-27B: a fine-tuned Qwen3.5 model built for value alignment and rich… — @HuggingModels
- Meet DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic: a 9B reasoning beast fine-tuned with… — @HuggingModels
- I always test the models I run for our local office agents. A launch post can't tell me… — @dedene
- Qwen 4 a little CRT cross section explainer. — @loktar00
- >be me — @LottoLabs
- 🚀 Qwen 3.8 27b NVFP4 inside TensorFold native CLI on @Windows 11 cooking on a @nvidia… — @ashxhart
- The quickest win in Ai security scanning is also the simplest. Static code analysis. — @AnchorWatch
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. 65.2k posts from 5k X accounts over the last 14 days, 10.6k tools, 19 markets. New posts are collected several times an hour and the full ranking is recomputed every hour — last update 2026-11-07 19:50 UTC. Full method.