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.
A Gemma 4 12B fine-tune for typed decisions that also chats and reads images. Ships as GGUF for llama.cpp, holds a 64K context on a 16 GB GPU, and serves /v1/systemone next to /v1/chat/completions.
Decides
choice, score, noul, classify, route
choice, score, noul, classify, route
Architecture
intern-decision
winnow
Fine-tuned from
qwen/qwen3.5-4b
google/gemma-4-12b-it
License
apache-2.0
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
80.6%
85.7%
Calibration error
—
—
Valid action rate
—
—
Median latency
44 ms
143 ms
p95 latency
44.6 ms
—
Evaluation suite
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 winnow?
intern-decision is from InternLM (Shanghai AI Laboratory) and winnow from EldanRing. Both have open weights you can download and run. Both answer choice, score, noul, classify and route questions. winnow reads up to 64K tokens of state, against 8K tokens for intern-decision. intern-decision is the smaller model, at 4.5B parameters to 12B.
Which is more accurate, intern-decision or winnow?
They report on different suites — intern-decision 80.6% on LocalLLaMA/typed-decisions test split (400 cases, 2,000 decisions), winnow 85.7% on JevBench public subset (231 items), Q8_0 — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, intern-decision or winnow?
intern-decision: Free (open weights). winnow: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Which is faster, intern-decision or winnow?
By their publishers’ figures, intern-decision answers in about 44 ms at the median and winnow in about 143 ms — measured on different hardware, so treat it as a rough guide.
Can I run intern-decision or winnow locally?
Yes, both: systemone pull internlm/intern-decision and systemone pull eldanring/winnow download the weights.
LocalLLaMA/typed-decisions test split (400 cases, 2,000 decisions)
