Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Log In
Sign Up
LargitData
/
gemma-4-26b-a4b-it-fp8
like
0
Follow
LargitData
3
Text Generation
Transformers
Safetensors
English
Chinese
gemma4
image-text-to-text
gemma-4
vllm
fp8
fp8-dynamic
compressed-tensors
quantization
h200
nvidia-h200
mixture-of-experts
Mixture of Experts
inference
production-ready
largitdata
conversational
License:
gemma
Model card
Files
Files and versions
xet
Community
Deploy
Use this model
main
gemma-4-26b-a4b-it-fp8
Ctrl+K
Ctrl+K
1 contributor
History:
6 commits
ywchiu
Update README: add MMLU-Pro accuracy (81.33% FP8 vs 81.59% BF16, -0.26 pp)
2398f3b
7 days ago
.gitattributes
Safe
1.71 kB
Add Gemma 4 26B-A4B IT FP8 Dynamic Norouter checkpoint and model card
8 days ago
README.md
Safe
13.2 kB
Update README: add MMLU-Pro accuracy (81.33% FP8 vs 81.59% BF16, -0.26 pp)
7 days ago
chat_template.jinja
Safe
12 kB
Add Gemma 4 26B-A4B IT FP8 Dynamic Norouter checkpoint and model card
8 days ago
config.json
Safe
5.3 kB
Add Gemma 4 26B-A4B IT FP8 Dynamic Norouter checkpoint and model card
8 days ago
generation_config.json
Safe
208 Bytes
Add Gemma 4 26B-A4B IT FP8 Dynamic Norouter checkpoint and model card
8 days ago
model-00001-of-00002.safetensors
Safe
26.3 GB
xet
Add files using upload-large-folder tool
7 days ago
model-00002-of-00002.safetensors
Safe
857 MB
xet
Add files using upload-large-folder tool
7 days ago
model.safetensors.index.json
Safe
130 kB
Add files using upload-large-folder tool
7 days ago
processor_config.json
Safe
1.69 kB
Add Gemma 4 26B-A4B IT FP8 Dynamic Norouter checkpoint and model card
8 days ago
tokenizer_config.json
Safe
2.07 kB
Add Gemma 4 26B-A4B IT FP8 Dynamic Norouter checkpoint and model card
8 days ago
