Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Website
Tasks
HuggingChat
Collections
Languages
Organizations
Community
Blog
Posts
Daily Papers
Learn
Discord
Forum
GitHub
Solutions
Team & Enterprise
Hugging Face PRO
Enterprise Support
Inference Providers
Inference Endpoints
Storage Buckets
Log In
Sign Up
mlboydaisuke
/
gemma-4-E2B-coreml
like
5
Image-Text-to-Text
Core ML
apple-silicon
ane
on-device
gemma-4
gemma-3n
multimodal
vision
audio
License:
gemma
Model card
Files
Files and versions
xet
Community
Copy to bucket
new
main
gemma-4-E2B-coreml
/
mf
/
chunk3.mlmodelc
326 MB
Ctrl+K
Ctrl+K
1 contributor
History:
2 commits
mlboydaisuke
Fused PLE (35 norms -> 1): smaller graph, faster iPhone compile
4a61cd0
verified
about 2 months ago
analytics
Fused PLE (35 norms -> 1): smaller graph, faster iPhone compile
about 2 months ago
weights
Multifunction chunks: SDPA decode + N=512 prefill, 50% weight dedup
about 2 months ago
coremldata.bin
pickle
Pickle imports
No problematic imports detected
What is a pickle import?
897 Bytes
xet
Multifunction chunks: SDPA decode + N=512 prefill, 50% weight dedup
about 2 months ago
metadata.json
16.7 kB
Multifunction chunks: SDPA decode + N=512 prefill, 50% weight dedup
about 2 months ago
model.mil
623 kB
Multifunction chunks: SDPA decode + N=512 prefill, 50% weight dedup
about 2 months ago
