# newTokenEra decision 27B by NewTokenEra

> newTokenEra decision 27B returns Chinese and English typed answers. It ships BF16 weights and code, with a 4,096-token limit per question.

Updated 2026-11-12 (Australia/Adelaide)

## Quick answers

### What is newTokenEra decision 27B by NewTokenEra?

[newTokenEra decision 27B](<https://decisionmodels.ai/models/newtokenera>): A Chinese/English post-trained Qwen3.8-27B decision model with full BF16 weights.

[newTokenEra decision 27B facts](<https://decisionmodels.ai/models/newtokenera>)

[Source](<https://huggingface.co/NewTokenEra/newTokenEra-decision-ct-Qwen3.8-27B>)

### Who makes newTokenEra decision 27B?

[newTokenEra decision 27B](<https://decisionmodels.ai/models/newtokenera>): NewTokenEra

[newTokenEra decision 27B facts](<https://decisionmodels.ai/models/newtokenera>)

[Source](<https://huggingface.co/NewTokenEra/newTokenEra-decision-ct-Qwen3.8-27B>)

By NewTokenEra · Hugging Face weight release: 2026-11-11 · OPEN

A Chinese/English post-trained Qwen3.8-27B decision model with full BF16 weights. Its decide method scores a 26-slot decision head once per question and returns Choice, Noul or Score answers, without generating text. Its reported N-bank evaluation was also used during interface development.

## Facts

- Base: Qwen/Qwen3.8-27B; upstream revision recorded in provenance.json
- Inputs: Text or JSON state; 1 to 64 questions; Choice has 2 to 26 options and Score has 2 to 10 ordered levels
- Context: 4,096 tokens per rendered question; longer inputs raise an error rather than truncate
- Access: 18 BF16 weight shards, about 52.17 GB before runtime overhead; custom Transformers code with trust\_remote\_code
- Calibration: Probabilities are conditional on supplied alternatives; downstream-domain calibration is unmeasured
- Licence: Apache-2.0; actual LICENSE included

## Claims and sources

- **VENDOR-REPORTED**: The maker reports 1,311/1,340 classification and Boolean decisions correct on the development N bank. Its 120 tied mixed decisions are excluded from accuracy; the 300 rating prompts use a separate MAE metric. This is a same-bank regression check. [source](<https://huggingface.co/NewTokenEra/newTokenEra-decision-ct-Qwen3.8-27B/blob/main/validation.json>)

## Links

- [Source: Card and weights](<https://huggingface.co/NewTokenEra/newTokenEra-decision-ct-Qwen3.8-27B>)
- [Source: Licence](<https://huggingface.co/NewTokenEra/newTokenEra-decision-ct-Qwen3.8-27B/blob/main/LICENSE>)
- [Source: Provenance](<https://huggingface.co/NewTokenEra/newTokenEra-decision-ct-Qwen3.8-27B/blob/main/provenance.json>)
- [Source: Evaluation record](<https://huggingface.co/NewTokenEra/newTokenEra-decision-ct-Qwen3.8-27B/blob/main/validation.json>)
- [Source: Typed inference implementation](<https://huggingface.co/NewTokenEra/newTokenEra-decision-ct-Qwen3.8-27B/blob/main/modeling_n97.py>)

## Related projects

No related projects are listed in the registry.