AI Agent StoreNace.AI · Local diffusion decision checkpoint
Drex DLM · local checkpoint
Run this decision model on your own hardware. Give it background information and questions with fixed answer options; it returns confidence scores instead of prose. It is based on Efficient-DLM-8B.
First reviewed 2026-10-11 · Checked 2026-10-15. The launch date has not been confirmed.
We still need comparable independent tests. You can compare the confirmed features and limits below, but we cannot yet give this version an Agent Fit or Practical Value rating. Test it on records with known answers, including cases that should go to a person.
What you can use today
You download the model files and supply the hardware and software to run them. Capacity is the amount of information a request can contain; settings and available memory can limit what fits.
Exact checkpoint ID: nace-ai/drex-dlm. The shared state uses bidirectional attention, with separate causal question branches and a pointer head. Requests inside the packed-token budget use one forward pass; larger ones split into question rows. This is a different checkpoint from Drex v1.5.
Weights are CC BY-NC 4.0, which does not grant ordinary commercial use. Runtime code is separately Apache 2.0. The provider reports tests on Apple M5 Max/M5 Pro and an H100; CPU-only inference is untested. These are vendor compatibility checks, not independently measured performance.
The exact card documents 32,768 maximum tokens, enabled explicitly; runners default to 16,384. Align the context, batch and microbatch caps. The provider has checked Q8_0 at 16,384; its full-window equivalence is not established by that test.
Output: Yes/no probabilities, multiple-choice probabilities and ordered rating scores. No generated explanation. Compare decision models, limits and input costs ↗
Native v1.5’s API price does not apply to this local diffusion checkpoint. About 16 GB BF16 weights are documented before overhead; hosted pricing and measured operating cost remain unknown. Repository creation October1 and later modification are artifact dates, not a verified launch date.
Provider release and specifications ↗
Check availability and plans ↗
Test it before switching
Give each model the same examples, tools and definition of success. Record correct outcomes, response time, retries and total cost. Include the time and hardware needed to run it.
Compare caching and long-context costs ↗