AI Agent StoreFrontiersMind · Download verified
Lumma-Fev 0.1B v2
Run simple ticket routing or topic classification locally with a small download. Test more demanding judgment tasks separately; small size does not imply comparable reasoning quality.
Announced 2026-10-29 · First reviewed 2026-10-30 · Checked 2026-11-03. The announcement and discovery dates do not establish ordinary API availability. Unverified prices remain unknown.
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 download ID: FrontiersMind/Lumma-fev-0.1B-v2. A 150-million-parameter model derived from Nandi-Mini-150M. It returns yes/no and choice probabilities, not a written answer. Score questions are accepted but untested by the publisher.
Downloadable Apache 2.0 weights, about 300 MB, using lumma-fev 0.4 or later. The publisher supports CPU or GPU use. Repository creation is October 30; an exact public release time is not established.
Shared text plus each question must fit in 2,048 tokens. Each question is evaluated independently. This model does not accept images.
No hosted token price or measured local operating cost is established. Publisher accuracy and calibration results remain separate from independent rankings.
Provider release and specifications ↗
Check availability and plans ↗
More setup and licensing details ↗
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 ↗