Skip to content

Qwen3.5-4B-typed-decisions

wozniakos10Decision modelOpen weights

Qwen3.5-4B-typed-decisions by wozniakos10 is a decision model: it answers typed questions with a probability for each allowed answer instead of generating text.

Pricing

No hosted price is listed. The weights are open: the cost is your own compute.

Specifications

Provider
wozniakos10
Parameters
4B
Released
Oct 2026
Open weights
Yes
Question types
Choice (one of N options), Score (ordered rubric), Yes / no
Mechanism
Decoder LM with a decision readout
Backbone
unsloth/Qwen3.5-4B
Jev-compatible request
Yes
Runs on CPU
No
License
apache-2.0
Hugging Face
wozniakos10/Qwen3.5-4B-typed-decisions

Self-reported by the publisher

The model's own claims, often on its own sets or a self-run copy of a public suite. Not independently verified and never ranked alongside measured results.

Typed Decisions (agreement with teacher)Self-reportedTyped Decisions test accuracy vs soft gold (fitted/fine-tuned on train; 400 cases / 2,000 decisions) · ECE 0.139
0.772
Typed DecisionsSelf-reported
0.772

Compare Qwen3.5-4B-typed-decisions with…

FAQ

How much does Qwen3.5-4B-typed-decisions cost?

Qwen3.5-4B-typed-decisions has no hosted price listed; its weights are open, so the cost is the compute you run it on.

What questions can Qwen3.5-4B-typed-decisions answer?

Qwen3.5-4B-typed-decisions answers choice (one of n options), score (ordered rubric), yes / no questions, returning a probability for each allowed answer.

Is Qwen3.5-4B-typed-decisions well calibrated?

No calibration measurement for Qwen3.5-4B-typed-decisions is recorded yet.

Is Qwen3.5-4B-typed-decisions open weight, and can it run on a CPU?

Yes, Qwen3.5-4B-typed-decisions has open weights. It needs a GPU to run at useful speed.

Data as of 2026-10-14. Source: Metatext decision-model catalogue, 2026-10-14 (Hugging Face). Pricing is per 1M tokens (USD); confirm with the provider before production use.