HEAD TO HEAD

anyjev vs intern-decision

Q: Can I run anyjev or intern-decision locally?

Yes, both: systemone pull nokia/anyjev and systemone pull internlm/intern-decision download the weights.

Nokia: anyjev and InternLM (Shanghai AI Laboratory): intern-decision, compared on what they decide, where they run, what they cost and what their publishers report.

The short version

Both have open weights you can download and run.
Both answer choice, score, noul, classify and route questions.
intern-decision is the smaller model, at 4.5B parameters to 8.0B.

Property	nokia/anyjev	internlm/intern-decision
Summary	A training-free layer that turns an open LLM into a decision model. It reads typed choice, yes/no and score answers from one prefill, removes option-order bias with no labels and, from a few hundred labels, calibrates or fits a closed-form head. Weights stay untouched.	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.
Decides	choice, score, noul, classify, route	choice, score, noul, classify, route
Architecture	anyjev	intern-decision
Fine-tuned from	qwen/qwen3-8b	qwen/qwen3.5-4b
License	apache-2.0	apache-2.0
Availability	Open weights	Open weights
Hosted by	—	—
Input price	—	—
Decision accuracy	77.1%	80.6%
Calibration error	0.034	—
Valid action rate	—	—
Median latency	—	44 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 anyjev and intern-decision?

anyjev is from Nokia and intern-decision from InternLM (Shanghai AI Laboratory). Both have open weights you can download and run. Both answer choice, score, noul, classify and route questions. intern-decision is the smaller model, at 4.5B parameters to 8.0B.

Which is more accurate, anyjev or intern-decision?

They report on different suites — anyjev 77.1% on LocalLLaMA/typed-decisions (2,000 held-out decisions), L2 with 300 labels per question, intern-decision 80.6% on LocalLLaMA/typed-decisions test split (400 cases, 2,000 decisions) — so the numbers do not rank them. Test both on your own labelled examples.

Which is cheaper, anyjev or intern-decision?

anyjev: Free (open weights). intern-decision: Free (open weights). Open weights cost nothing per call beyond your own hardware.

Can I run anyjev or intern-decision locally?

Yes, both: systemone pull nokia/anyjev and systemone pull internlm/intern-decision download the weights.

nokia/anyjev

internlm/intern-decision

Summary

A training-free layer that turns an open LLM into a decision model. It reads typed choice, yes/no and score answers from one prefill, removes option-order bias with no labels and, from a few hundred labels, calibrates or fits a closed-form head. Weights stay untouched.

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.

Decides

choice, score, noul, classify, route

Architecture

anyjev

intern-decision

Fine-tuned from

qwen/qwen3-8b

qwen/qwen3.5-4b

License

apache-2.0

Availability

Open weights

Hosted by

—

Input price

—

Decision accuracy

77.1%

80.6%

Calibration error

0.034

—

Valid action rate

—

Median latency

—

44 ms

p95 latency

—

44.6 ms