linne-fern 1.0 (27B)
linne-fern 1.0 (27B) by MISA-AICORE is a decision model: it answers typed questions with a probability for each allowed answer instead of generating text. It scores 57.8 on the Jev Decision Index (rank 20).
Pricing
No hosted price is listed. The weights are open: the cost is your own compute.
Specifications
- Provider
- MISA-AICORE
- 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
- Yes
- Runs on CPU
- No
- License
- apache-2.0
- Hugging Face
- MISA-core/linne-fern-1-0
Benchmarks
- Jev Decision IndexECE 0.079
- 57.8
Jev Decision Index: public 58.9, ECE 0.079, Brier 0.360. 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
- 58.9
Speed & latency
Compare linne-fern 1.0 (27B) with…
FAQ
How much does linne-fern 1.0 (27B) cost?
linne-fern 1.0 (27B) has no hosted price listed; its weights are open, so the cost is the compute you run it on.
What questions can linne-fern 1.0 (27B) answer?
linne-fern 1.0 (27B) answers choice (one of n options), score (ordered rubric), yes / no questions, returning a probability for each allowed answer.
Is linne-fern 1.0 (27B) well calibrated?
On the Jev Decision Index its expected calibration error (ECE) is 0.079; below about 0.05, a stated 80% confidence is right roughly 80% of the time.
Is linne-fern 1.0 (27B) open weight, and can it run on a CPU?
Yes, linne-fern 1.0 (27B) 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.