Qwen-2.5-1B-RLCD
Qwen-2.5-1B-RLCD by harshatheg is a decision model: it answers typed questions with a probability for each allowed answer instead of generating text. It scores 3.9 on the Jev Decision Index (rank 153).
Pricing
No hosted price is listed. The weights are open: the cost is your own compute.
Specifications
- Provider
- harshatheg
- Parameters
- 2B
- Released
- Sep 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/Qwen2.5-1.5B
- Jev-compatible request
- No
- Runs on CPU
- No
- License
- apache-2.0
- Hugging Face
- harshatheg/Qwen-2.5-1B-RLCD
Benchmarks
- Jev Decision IndexECE 0.205
- 3.9
Jev Decision Index: public 4.0, ECE 0.205, Brier 0.793. Lower ECE means its probabilities can be taken at face value.
Speed & latency
Compare Qwen-2.5-1B-RLCD with…
FAQ
How much does Qwen-2.5-1B-RLCD cost?
Qwen-2.5-1B-RLCD has no hosted price listed; its weights are open, so the cost is the compute you run it on.
What questions can Qwen-2.5-1B-RLCD answer?
Qwen-2.5-1B-RLCD answers choice (one of n options), score (ordered rubric), yes / no questions, returning a probability for each allowed answer.
Is Qwen-2.5-1B-RLCD well calibrated?
On the Jev Decision Index its expected calibration error (ECE) is 0.205; below about 0.05, a stated 80% confidence is right roughly 80% of the time.
Is Qwen-2.5-1B-RLCD open weight, and can it run on a CPU?
Yes, Qwen-2.5-1B-RLCD 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.