amos-1-large
amos-1-large by Scira (mukaddamzaid) 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
- Scira (mukaddamzaid)
- Parameters
- —
- 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
- —
- License
- apache-2.0
- Hugging Face
- mukaddamzaid/amos-1-large
Benchmarks
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.
- Typed Decisions (agreement with teacher)Self-reportedTyped Decisions test accuracy vs soft gold (fitted/fine-tuned on train; 400 cases / 2,000 decisions)
- 0.802
- jev-decision-index-vision-publicSelf-reported
- 76.0
Compare amos-1-large with…
FAQ
How much does amos-1-large cost?
amos-1-large has no hosted price listed; its weights are open, so the cost is the compute you run it on.
What questions can amos-1-large answer?
amos-1-large answers choice (one of n options), score (ordered rubric), yes / no questions, returning a probability for each allowed answer.
Is amos-1-large well calibrated?
No calibration measurement for amos-1-large is recorded yet.
Is amos-1-large open weight, and can it run on a CPU?
Yes, amos-1-large has open weights.
Data as of 2026-10-14. Source: Metatext decision-model catalogue, 2026-10-14 (Benchmark Heaven JevBench, Hugging Face). Pricing is per 1M tokens (USD); confirm with the provider before production use.