Bosun v3.1 0.6B
Bosun v3.1 0.6B by Hanno Labs is a decision model: it answers typed questions with a probability for each allowed answer instead of generating text. It scores 8.7 on the Jev Decision Index (rank 143).
Pricing
No hosted price is listed. The weights are open: the cost is your own compute.
Specifications
- Provider
- Hanno Labs
- Parameters
- 596M
- 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/Qwen3-0.6B-Base
- Jev-compatible request
- Yes
- Runs on CPU
- Yes
- License
- apache-2.0
- Hugging Face
- Hanno-Labs/bosun-v3.1-0.6b
Benchmarks
- Jev Decision IndexECE 0.142
- 8.7
- DecisionBenchECE 0.066
- 0.812
Jev Decision Index: public 14.5, ECE 0.142, Brier 0.667. Lower ECE means its probabilities can be taken at face value.
Speed & latency
Compare Bosun v3.1 0.6B with…
FAQ
How much does Bosun v3.1 0.6B cost?
Bosun v3.1 0.6B has no hosted price listed; its weights are open, so the cost is the compute you run it on.
What questions can Bosun v3.1 0.6B answer?
Bosun v3.1 0.6B answers choice (one of n options), score (ordered rubric), yes / no questions, returning a probability for each allowed answer.
Is Bosun v3.1 0.6B well calibrated?
On the Jev Decision Index its expected calibration error (ECE) is 0.142; below about 0.05, a stated 80% confidence is right roughly 80% of the time.
Is Bosun v3.1 0.6B open weight, and can it run on a CPU?
Yes, Bosun v3.1 0.6B has open weights. It is small enough to run on a CPU.
Data as of 2026-10-14. Source: Metatext decision-model catalogue, 2026-10-14 (Jev Decision Index, DecisionBench, Enterprise Decision Arena, Hugging Face). Pricing is per 1M tokens (USD); confirm with the provider before production use.