Downloads · 30 days
35
43% of all-time downloads
gemma-4-26B-A4B-AutoRound-MXFP8
LeaderboardModel1/gemma-4-26B-A4B-AutoRound-MXFP8
gemma-4-26B-A4B-AutoRound-MXFP8 is a text generation model from LeaderboardModel1. Use it when you need the model to write or continue text.
This is a MXFP8 quantization of google/gemma-4-26B-A4B, generated by AutoRound. Please follow the license of the original model.
All-time downloads
82
Public
Parameters
25.8B
17.6 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors17.6 GB · 100%
Parameter types
How the weights are stored.
U822.8B · 88%
Try a prompt
Base models
Model card
From the Hugging Face model README
gemma-4-26B-A4B-AutoRound-MXFP8
Model Details
This is a MXFP8 quantization of google/gemma-4-26B-A4B, generated by AutoRound. Please follow the license of the original model.
Quantization Details
- Scheme: MXFP8
- Method: AutoRound
- Base model: google/gemma-4-26B-A4B
Evaluation
| Benchmark | Score |
|---|---|
| gsm8k | 0.5747 |
| hellaswag | 0.8265 |
| mmlu | 0.7391 |
| piqa | 0.8226 |
Produced with autoquant-agent — agent-driven quantize + evaluate + self-heal.
- Task
- Text Generation
- Type
- gemma4
- Created
- Aug 24, 2026
- Updated
- Aug 24, 2026