Qwen-Jeff B2
Qwen-Jeff B2 by divergentlabs 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
- divergentlabs
- 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
- Qwen3-1.7B, scalar readout
- Jev-compatible request
- No
- Runs on CPU
- No
- License
- Apache 2.0
- Hugging Face
- divergentlabs/qwen-jeff-B2
Compare Qwen-Jeff B2 with…
FAQ
How much does Qwen-Jeff B2 cost?
Qwen-Jeff B2 has no hosted price listed; its weights are open, so the cost is the compute you run it on.
What questions can Qwen-Jeff B2 answer?
Qwen-Jeff B2 answers choice (one of n options), score (ordered rubric), yes / no questions, returning a probability for each allowed answer.
Is Qwen-Jeff B2 well calibrated?
No calibration measurement for Qwen-Jeff B2 is recorded yet.
Is Qwen-Jeff B2 open weight, and can it run on a CPU?
Yes, Qwen-Jeff B2 has open weights. It needs a GPU to run at useful speed.
Data as of 2026-10-14. Source: Metatext System One registry (metatext.io/system-one). Pricing is per 1M tokens (USD); confirm with the provider before production use.