GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
AxionML
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
AxionML
Model Tree
google/gemma-4-31B-it
Input Modalities
Output Modalities
Supported Functionality
| Architecture | Dense transformer, hybrid sliding-window + global attention, p-RoPE |
| Parameters | 30.7B |
| Input | Text, image, video (as frames) |
| Context Length | 256K tokens |
| Vocabulary Size | 262,144 |
| Checkpoint Size | ~32.6 GB |
| Benchmark | BF16 | NVFP4 |
|---|---|---|
| GPQA Diamond | 85.80 | 85.35 |
| AIME 2025 | 87.92 | 87.60 |
| MMLU Pro | 85.25 | 84.94 |
| LiveCodeBench (pass@1) | 82.49 | 82.27 |
| SciCode subtask acc (pass@1) | 33.61 | 33.18 |
| Terminal-Bench Hard (pass@1) | 27.08 | 27.08 |
Scores reported by NVIDIA for this checkpoint.
temperature=1.0,top_p=0.95,max_new_tokens=131072.
lm_head and the vision tower kept in BF16bash
python3 -m sglang.launch_server \ --model-path AxionML/Gemma-4-31B-NVFP4 \ --quantization modelopt_fp4 \ --tp 1 \ --reasoning-parser gemma4 \ --tool-call-parser gemma4bash
vllm serve AxionML/Gemma-4-31B-NVFP4 \ --quantization modelopt \ --tensor-parallel-size 8Sister checkpoint: AxionML/Gemma-4-12B-NVFP4 uses the same MLP-only recipe.
The base model was trained on data that may contain toxic language and societal biases. The quantized model inherits these limitations. It may generate inaccurate, biased, or offensive content. Please refer to the original model card and the upstream quantized model card for full details.
python3 -m sglang.launch_server \ --model-path AxionML/Gemma-4-31B-NVFP4 \ --quantization modelopt_fp4 \ --tp 1 \ --reasoning-parser gemma4 \ --tool-call-parser gemma4vllm serve AxionML/Gemma-4-31B-NVFP4 \ --quantization modelopt \ --tensor-parallel-size 8