Nace AI Open-Sources Drex Max v1 27B Decision Model
Original title: Nace AI Open-Sources Drex Max v1: A 27B Decision Model That Runs Locally on Apple Silicon
Drex Max v1 27B decision model is open-sourced by Nace AI for local inference on Apple Silicon.
Nace AI released Drex Max v1 as open weights. The 27B model answers questions about context including text JSON and images returning option probabilities. It supports 262144 token context and runs on Apple Silicon Macs with 24 GB or more RAM using affine Q4 quantization.
- Scores 67.52 on public Decision Index 0.4
- Runs via Kapitsa or MLX on Apple Silicon
- Q80 GGUF requires 48 GB RAM
- Affine Q4 checkpoint targets 24 GB Macs
- Vendors
- Nace AI
- AI models
- Drex Max v1
From the original article
7 min read at marktechpost.comNace AI open-sources Drex Max v1, a 27B multimodal decision model scoring 67. 52 that runs on Apple Silicon. The post Nace AI Open-Sources Drex Max v1: A 27B Decision Model That Runs Locally on Apple Silicon appeared first on MarkTechPost.
By Asif Razzaq · marktechpost.com
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.