Metask Lab's calibrated decision model in 16 languages. Qwen3.5-4B with a merged LoRA trained with the Nimble candidate-logit objective; one forward pass and a softmax over at most 26 answer-letter logits, with one temperature per question type.
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
metask-jev
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
80.1%
85.7%
Calibration error
—
—
Valid action rate
—
—
Median latency
62.8 ms
143 ms
p95 latency
—
—
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 metask-jev and winnow?
metask-jev is from Metask Lab 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 4K tokens for metask-jev. metask-jev is the smaller model, at 4.5B parameters to 12B.
Which is more accurate, metask-jev or winnow?
They report on different suites — metask-jev 80.1% on JevBench v1.2 public set (231 items) at 4,096 tokens, maker's run, 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, metask-jev or winnow?
metask-jev: Free (open weights). winnow: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Which is faster, metask-jev or winnow?
By their publishers’ figures, metask-jev answers in about 62.8 ms at the median and winnow in about 143 ms — measured on different hardware, so treat it as a rough guide.
Can I run metask-jev or winnow locally?
Yes, both: systemone pull metask-lab/metask-jev and systemone pull eldanring/winnow download the weights.
JevBench v1.2 public set (231 items) at 4,096 tokens, maker's run
