GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
PoSTMEDIA
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
PoSTMEDIA
Model Tree
google/gemma-4-31B-it
Input Modalities
Output Modalities
Supported Functionality
| Specification | Details |
|---|---|
| Base Model | google/gemma-4-31B-it |
| Parameters | 31B (dense) |
| Architecture | Decoder-only Transformer (dense) |
| Training Precision | BF16 |
| Inference Precision | BF16 |
| Context Length | Inherits from Gemma-4 base |
| Fine-Tuning Method | Full-parameter SFT (Capability-Preserving recipe, 2nd gen) |
| Languages | Korean, English |
All results below were measured in-house under a single unified protocol (identical prompts, sampling, and generation budgets for both models).
| Benchmark | gemma-4-31B-it (base) | Lux-V1-Pro | Lux-V2-Pro |
|---|---|---|---|
| MMLU | 86.6 | 85.9 | 86.6 |
| AIME 2024 | 83.3 | 80.0 | 93.3 |
| AIME 2025 | 66.7 | 63.3 | 76.7 |
| HMMT 2025 | 70.0 | 60.0 |
The full 18-benchmark suite shows 16 wins, 1 tie (GPQA), and 2 minor regressions (GSM8K −1.2, IFBench −0.2) versus Lux-V1-Pro. Averaged over the 17 benchmarks measured for all three models, Lux-V2-Pro scores 78.2 — above both the original Gemma-4 base (76.6) and Lux-V1-Pro (75.5). (MMLU-Pro was not measured for the base model due to generation-budget constraints.)
The V2 generation is trained on PoSTMEDIA's in-house Korean synthetic data assets, generated and quality-controlled by our internal data factory:
Correctness of the synthetic data is enforced by verification gates (code execution, symbolic math equivalence, rule checkers, and source-grounding checks) rather than by model self-judgment.
The exact training procedure — schedule, module selection, and the post-training consolidation step that preserves base capability — is an internal research method and is not disclosed in detail.
bash
pip install transformers accelerate
python
from transformers import AutoModelForCausalLM, AutoTokenizerimport torchmodel_name = "PoSTMEDIA/Lux-V2-Pro"tokenizer = AutoTokenizer.from_pretrained(model_name)model = AutoModelForCausalLM.from_pretrained(model_name,torch_dtype=torch.bfloat16,device_map="auto",)messages = [{"role": "user", "content": "문화재보호법의 목적을 두 문장으로 설명해줘."}]inputs = tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt").to(model.device)outputs = model.generate(inputs, max_new_tokens=512)print(tokenizer.decode(outputs[0][inputs.shape[1]:], skip_special_tokens=True))
bibtex
@misc{lux2026pro,title = {Lux-V2-Pro: Capability-Preserving Korean Domain Adaptation of Gemma-4},author = {{PoSTMEDIA AI Lab}},year = {2026},url = {https://huggingface.co/PoSTMEDIA/Lux-V2-Pro}}
Questions and feedback — please open a discussion on the model page.
| 63.3 |
| IFEval | 93.2 | 92.4 | 93.7 |
| KMMLU | 76.6 | 74.8 | 76.9 |
| KMMLU-Pro | 78.2 | 77.0 | 77.4 |
| CLIcK | 85.1 | 84.8 | 85.5 |
| KoBALT | 73.4 | 71.9 | 73.9 |
| HAE-RAE Bench | 82.0 | 80.6 | 83.1 |
| HRM8K | 85.8 | 84.7 | 85.8 |
| KoSimpleQA | 91.2 | 90.0 | 90.8 |
| KoSQA-EM | 38.0 | 36.1 | 38.5 |
| Average (17 common benchmarks) | 76.6 | 75.5 | 78.2 |