Radar / AI models / Drex Max v1 open weights

Drex Max v1 open weights: Nace AI's 27B decision model, now runnable locally

Open weights for Nace AI's 27-billion-parameter decision model: it returns a probability for every option in a single forward pass, with a 262,144-token window and image input, and runs on consumer Apple Silicon Macs and NVIDIA GPUs.

new launchmodels · decisionJEV traction 0.37added 2026-11-01
Open Drex Max v1 open weights →View on the radar

Why it matters

A decision model, not a chatbot: calibrated probabilities instead of generated text, now as open weights that can run locally rather than only through a hosted API.

What you could build with it

An audit team could route invoice approvals through a decision model like this: each invoice plus its supporting documents becomes a state, typed questions ask whether the amount matches and the vendor is approved, and only low-confidence cases reach a human reviewer.

Does it hold up?

Usable now via the hosted API and, with the open weights, locally on machines with 24 GB or more of memory; the Q8 checkpoint needs 48 GB, so local use is limited to well-specced hardware.

Built with Drex Max v1 open weights

Learn more

technical deep dive →

First spotted on article: source.

More AI models

VoiceStudio: open-source, fully-local ElevenLabs alternative for voice cloning, dubbing, and audiobooksdebpalash/VoiceStudio is a desktop app that runs voice cloning, voice design, video dubbing, dictation, transcription…models · JEV 0.75Tencent Hunyuan Hy3: open 295B MoE with 21B active under Apache 2.0Tencent open-sourced Hy3, a 295B-parameter mixture-of-experts model with only 21B parameters active per token, under…models · JEV 0.73NVIDIA Isaac Lab 3.0 GA + Isaac OS open runtime + Agile ONE SN humanoidMajor Isaac platform expansion at GTC Berlin Oct 21: Isaac Lab 3.0 is generally available as the open-source robot…models · JEV 0.73NVIDIA Nemotron 3.5 Retriever collection: Embed 8B/1B, Rerank 8B, Parse 631MNVIDIA's Oct 21 collection drop for agentic retrieval: Nemotron-3.5-Embed in 8B BF16, 1B BF16 and 1B NVFP4…models · JEV 0.72Kimi K3.1 Pro: Moonshot's 2.8T open-weight flagship officially launchesMoonshot AI officially launched Kimi K3.1 Pro on Oct 23, a mixture-of-experts model with 2.8 trillion total / 104…models · JEV 0.72NVIDIA Cosmos 3.5 world models: now openly availableNVIDIA's Cosmos 3.5 family of open world foundation models for robots, autonomous vehicles and vision agents is now…models · JEV 0.71

Get the week's best AI launches, plus 3 ideas worth building

One email every Saturday. Ranked by traction, not hype. Free.