The flagship of the vLLM Semantic Router team's Decision 1.0 family. Qwen3.5-9B with a shared candidate head returns a probability for every supplied answer to choice, yes/no and score questions, over a 16,384-token input.
FrontiersMind's decision model on a base it pre-trained from scratch. Each question reads the state and its own tokens once and a 256-dimension pointer head scores the options; Choice and Score take up to 255 entries, and nothing is generated.
Decides
choice, score, noul, classify, route
choice, score, noul
Architecture
decision
lumma-fev
Fine-tuned from
qwen/qwen3.5-9b
frontiersmind/lumma-0.6b-base
License
apache-2.0
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
77.4%
64.0%
Calibration error
—
—
Valid action rate
—
—
Median latency
—
45.8 ms
p95 latency
—
—
Figures are from each model’s manifest; accuracy and latency are what the publishers report, on their own suites and hardware. Add a third model.
Questions
What is the difference between decision and lumma-fev?
decision is from vLLM Semantic Router and lumma-fev from FrontiersMind. Both have open weights you can download and run. Both answer choice, score and noul questions. Only decision answers classify and route. decision reads up to 16K tokens of state, against 8K tokens for lumma-fev. lumma-fev is the smaller model, at 649M parameters to 9.0B.
Which is more accurate, decision or lumma-fev?
They report on different suites — decision 77.4% on vLLM-SR decision benchmark (54 tasks, 3,766 decisions, weighted), lumma-fev 64.0% on typed-decisions (maker's table; split not stated) — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, decision or lumma-fev?
decision: Free (open weights). lumma-fev: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run decision or lumma-fev locally?
Yes, both: systemone pull vllm-semantic-router/decision and systemone pull frontiersmind/lumma-fev download the weights.
