KnowLine-35B-A3B-Gen1
KnowLine-35B-A3B-Gen1 by PelaAI is a decision model: it answers typed questions with a probability for each allowed answer instead of generating text. It scores 62.9 on the Jev Decision Index (rank 9).
Pricing
No hosted price is listed. The weights are open: the cost is your own compute.
Specifications
- Provider
- PelaAI
- Parameters
- 36B
- 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/Qwen3.5-35B-A3B
- Jev-compatible request
- Yes
- Runs on CPU
- No
- License
- apache-2.0
- Hugging Face
- PelaAI/KnowLine-35B-A3B-Gen1
Benchmarks
- Jev Decision IndexECE 0.048
- 62.9
- Jev Decision Index — VisionECE 0.011
- 68.1
Jev Decision Index: public 69.5, ECE 0.048, Brier 0.261. Lower ECE means its probabilities can be taken at face value.
Speed & latency
Compare KnowLine-35B-A3B-Gen1 with…
FAQ
How much does KnowLine-35B-A3B-Gen1 cost?
KnowLine-35B-A3B-Gen1 has no hosted price listed; its weights are open, so the cost is the compute you run it on.
What questions can KnowLine-35B-A3B-Gen1 answer?
KnowLine-35B-A3B-Gen1 answers choice (one of n options), score (ordered rubric), yes / no questions, returning a probability for each allowed answer.
Is KnowLine-35B-A3B-Gen1 well calibrated?
On the Jev Decision Index its expected calibration error (ECE) is 0.048; below about 0.05, a stated 80% confidence is right roughly 80% of the time.
Is KnowLine-35B-A3B-Gen1 open weight, and can it run on a CPU?
Yes, KnowLine-35B-A3B-Gen1 has open weights. It needs a GPU to run at useful speed.
Data as of 2026-10-19. Source: Metatext decision-model catalogue, 2026-10-14 (Hugging Face). Pricing is per 1M tokens (USD); confirm with the provider before production use.