Shanghai AI Laboratory's multimodal decision model. A fine-tune of Qwen3.5-4B's language backbone (vision tower frozen) that answers up to 16 Choice, Score and Noul questions about a state and up to eight images in one forward pass, with a fitted calibration temperature.
StartLux's decision family in five sizes, 0.8B to 27B. All questions in a request are answered in one forward pass, with a probability for every option, through a TypeSafe /v1/systemone-compatible server that records CUDA graphs for short requests.
Decides
choice, score, noul, classify, route
choice, score, noul
Architecture
intern-decision
startlux-decision
Fine-tuned from
qwen/qwen3.5-4b
—
License
apache-2.0
cc-by-nc-4.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
80.6%
88.3%
Calibration error
—
—
Valid action rate
—
—
Median latency
44 ms
26 ms
p95 latency
44.6 ms
—
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 intern-decision and startlux-decision?
intern-decision is from InternLM (Shanghai AI Laboratory) and startlux-decision from StartLux. Both have open weights you can download and run. Both answer choice, score and noul questions. Only intern-decision answers classify and route. intern-decision is the smaller model, at 4.5B parameters to 4.7B. intern-decision is licensed apache-2.0; startlux-decision, cc-by-nc-4.0.
Which is more accurate, intern-decision or startlux-decision?
They report on different suites — intern-decision 80.6% on LocalLLaMA/typed-decisions test split (400 cases, 2,000 decisions), startlux-decision 88.3% on JevBench public set (231 items; 204 correct), maker's run — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, intern-decision or startlux-decision?
intern-decision: Free (open weights). startlux-decision: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Which is faster, intern-decision or startlux-decision?
By their publishers’ figures, startlux-decision answers in about 26 ms at the median and intern-decision in about 44 ms — measured on different hardware, so treat it as a rough guide.
Can I run intern-decision or startlux-decision locally?
Yes, both: systemone pull internlm/intern-decision and systemone pull startlux/startlux-decision download the weights.
Evaluation suite
LocalLLaMA/typed-decisions test split (400 cases, 2,000 decisions)
JevBench public set (231 items; 204 correct), maker's run
