Lumma-fev-0.6b

FrontiersMindDecision modelOpen weights

Lumma-fev-0.6b by FrontiersMind is a decision model: it answers typed questions with a probability for each allowed answer instead of generating text.

Pricing

No hosted price is listed. The weights are open: the cost is your own compute.

Specifications

Provider: FrontiersMind
Parameters: 649M
Released: Sep 2026
Open weights: Yes
Question types: Choice (one of N options), Score (ordered rubric), Yes / no
Mechanism: Encoder classifier
Backbone: FrontiersMind/Lumma-0.6B-Base
Jev-compatible request: Yes
Runs on CPU: Yes
License: apache-2.0
Hugging Face: FrontiersMind/Lumma-fev-0.6b

Benchmarks

Jev Decision Indexedition 0.2.1 (earlier edition): 3.0

Compare Lumma-fev-0.6b with…

Lumma-fev-0.6b vs amos-1-large—/1M in Lumma-fev-0.6b vs amos-1-medium—/1M in Lumma-fev-0.6b vs Celeris-1 Decision$0.04/1M in Lumma-fev-0.6b vs ScaleDown Classify-1$0.04/1M in Lumma-fev-0.6b vs Cloudflare clef—/1M in Lumma-fev-0.6b vs Cloudflare clef-flash—/1M in

FAQ

How much does Lumma-fev-0.6b cost?

Lumma-fev-0.6b has no hosted price listed; its weights are open, so the cost is the compute you run it on.

What questions can Lumma-fev-0.6b answer?

Lumma-fev-0.6b answers choice (one of n options), score (ordered rubric), yes / no questions, returning a probability for each allowed answer.

Is Lumma-fev-0.6b well calibrated?

No calibration measurement for Lumma-fev-0.6b is recorded yet.

Is Lumma-fev-0.6b open weight, and can it run on a CPU?

Yes, Lumma-fev-0.6b has open weights. It is small enough to run on a CPU.

Data as of 2026-10-14. Source: Metatext decision-model catalogue, 2026-10-14 (Jev Decision Index, Enterprise Decision Arena, Hugging Face). Pricing is per 1M tokens (USD); confirm with the provider before production use.