GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
PNPM244
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
PNPM244
Model Tree
google/gemma-4-31B-it
Input Modalities
Output Modalities
Supported Functionality
Full score = 20% public benchmarks + 50% private tests of the same skills + 30% private tasks from new domains, all run by the leaderboard maintainers. Snapshot of 2026-10-14.
| Model | Full | Public | Private, same skills | Private, new domains |
|---|---|---|---|---|
| vLLM-SR d3 (27B) | 66.26 | 65.45 | 62.83 | 60.51 |
| linne-oak-1.0 (31B) | 65.61 | 63.94 | 62.44 | 60.12 |
| Decider 31B (NVFP4) | 64.62 | 64.27 | 61.79 | 58.32 |
| Sieve 31B | 63.81 | 62.52 | 60.89 | 58.31 |
| Perplexity Decider v1.1 (27B) | 62.75 | 62.25 | 61.10 | 55.57 |
| linne-fern-1.0 (27B) | 57.81 | 58.92 | 56.52 | 50.71 |
The private parts were run by the maintainers with our serving code; their answers agreed with our submitted run on 99.51% of the validation rows.
Fine-tuned from google/gemma-4-31B-it on decision-format data (state, question, options) covering
classification, NLI, retrieval, tool selection and agent safety, in English and Vietnamese.
The training data is not released.
The prompt is one user message (chat template, thinking off): the state (compact JSON when not a string), a blank line,
Question: <instructions>, one line <label>: <name> - <description> per option, and
Answer with the letter of one option only. The answer is the softmax over the next-token logits of the option letters
(with the model's final logit soft-capping), read at the last prompt position, with the full-attention layers bidirectional.
linne_engine.py (with nc_hook.py) in this repository implements exactly this, as a Decision Index engine and as a library:
python
import sysfrom huggingface_hub import snapshot_download path = snapshot_download("MISA-core/linne-oak-1-0")sys.path.insert(0, path)from linne_engine import LinneEngine model = LinneEngine(model=path, device="cuda:0", noncausal=True)result, _ = model( "My Stripe integration keeps failing. Please help ASAP.", {"team": {"type": "choice", "instructions": "Which team should handle this request?", "criteria": {"billing": "Charges and refunds", "technical_support": "Integration errors", "sales": "Questions about buying a product"}}},)print(result["answers"]["team"]) # chosen option and a probability for every optionRun the Decision Index public suite:
text
PYTHONPATH=<path> python -m decision_index pipeline --engine linne_engine:LinneEngine \ --option model=<path> --option device=cuda:0 --option noncausal=1 --out runs/linne-oak-1-0BF16 weights are about 62 GB and fit one 80 GB GPU.
Apache 2.0, following the base model's license.
If you use linne-oak-1.0 in your research or applications, please cite this model:
bibtex
@misc{linne_oak_1_0, title = {linne-oak-1.0: A 31B Non-Causal Decision Model}, author = {Tran, Minh Duc}, year = {2026}, howpublished = {\url{https://huggingface.co/PNPM244/linne-oak-1-0}}, note = {Version 1.0}}import sysfrom huggingface_hub import snapshot_download path = snapshot_download("MISA-core/linne-oak-1-0")sys.path.insert(0, path)from linne_engine import LinneEngine model = LinneEngine(model=path, device="cuda:0", noncausal=True)result, _ = model( "My Stripe integration keeps failing. Please help ASAP.", {"team": {"type": "choice", "instructions": "Which team should handle this request?", "criteria": {"billing": "Charges and refunds", "technical_support": "Integration errors", "sales": "Questions about buying a product"}}},)print(result["answers"]["team"]) # chosen option and a probability for every optionPYTHONPATH=<path> python -m decision_index pipeline --engine linne_engine:LinneEngine \ --option model=<path> --option device=cuda:0 --option noncausal=1 --out runs/linne-oak-1-0@misc{linne_oak_1_0, title = {linne-oak-1.0: A 31B Non-Causal Decision Model}, author = {Tran, Minh Duc}, year = {2026}, howpublished = {\url{https://huggingface.co/PNPM244/linne-oak-1-0}}, note = {Version 1.0}}