Downloads · 30 days
33
72% of all-time downloads
gemma-4-31B-MXFP8-CT-AutoRound
INCModel3/gemma-4-31B-MXFP8-CT-AutoRound
gemma-4-31B-MXFP8-CT-AutoRound is a text generation model from INCModel3. Use it when you need the model to write or continue text.
This is a MXFP8 quantization of google/gemma-4-31B, generated by AutoRound. Please follow the license of the original model.
All-time downloads
46
Public
Parameters
31.3B
34.2 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors34.2 GB · 100%
Parameter types
How the weights are stored.
F8_E4M329.3B · 94%
Try a prompt
Base models
Model card
From the Hugging Face model README
gemma-4-31B-AutoRound-MXFP8
Model Details
This is a MXFP8 quantization of google/gemma-4-31B, generated by AutoRound. Please follow the license of the original model.
Quantization Details
- Scheme: MXFP8
- Method: AutoRound
- Base model: google/gemma-4-31B
Evaluation
| Benchmark | Score |
|---|---|
| gsm8k | 0.8597 |
| hellaswag | 0.8522 |
| mmlu | 0.8111 |
| piqa | 0.8264 |
Produced with autoquant-agent — agent-driven quantize + evaluate + self-heal.
- Task
- Text Generation
- Type
- gemma4
- Created
- Aug 21, 2026
- Updated
- Aug 21, 2026