Qwen Decision 27B noncausal LoRA
Qwen Decision 27B noncausal LoRA by jsaurabh is a decision model: it answers typed questions with a probability for each allowed answer instead of generating text. It scores 58.5 on the Jev Decision Index (rank 17).
Pricing
No hosted price is listed. The weights are open: the cost is your own compute.
Specifications
- Provider
- jsaurabh
- Parameters
- 28B
- 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
- Qwen/Qwen3.8-27B
- Jev-compatible request
- No
- Runs on CPU
- No
- License
- apache-2.0
- Hugging Face
- jsaurabh/qwen-decision-27b-noncausal-lora
Benchmarks
- Jev Decision IndexECE 0.051
- 58.5
Jev Decision Index: public 57.7, ECE 0.051, Brier 0.358. Lower ECE means its probabilities can be taken at face value.
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.
- Jev Decision Index public suite (self-run)Self-reportedDecision Index public balanced skill, edition 0.3 kit (release-v3), self-run
- 57.7
Speed & latency
Compare Qwen Decision 27B noncausal LoRA with…
FAQ
How much does Qwen Decision 27B noncausal LoRA cost?
Qwen Decision 27B noncausal LoRA has no hosted price listed; its weights are open, so the cost is the compute you run it on.
What questions can Qwen Decision 27B noncausal LoRA answer?
Qwen Decision 27B noncausal LoRA answers choice (one of n options), score (ordered rubric), yes / no questions, returning a probability for each allowed answer.
Is Qwen Decision 27B noncausal LoRA well calibrated?
On the Jev Decision Index its expected calibration error (ECE) is 0.051; below about 0.05, a stated 80% confidence is right roughly 80% of the time.
Is Qwen Decision 27B noncausal LoRA open weight, and can it run on a CPU?
Yes, Qwen Decision 27B noncausal LoRA 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 (Jev Decision Index, Hugging Face). Pricing is per 1M tokens (USD); confirm with the provider before production use.