Downloads · 30 days
1.1K
75% of all-time downloads
Gemma-4-E2B-IT-QAT
pleasen/Gemma-4-E2B-IT-QAT
Gemma-4-E2B-IT-QAT is a machine learning model from pleasen. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Optimized for resource-constrained and mobile deployment through targeted architectural and numerical optimizations.
All-time downloads
1.5K
Public
Repo size
10.5 GB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.gguf3 GB · 100%
At a glance
- Access
- Public
- Created
- Sep 23, 2026
- Updated
- Oct 17, 2026
- SHA
- b23c2222
Model card
From the Hugging Face model README
Optimized for resource-constrained and mobile deployment through targeted architectural and numerical optimizations.
Audio encoders removed to reduce the overall model footprint.
Vision layers quantized to Q8_0 or Q4_0 substantially reduced storage requirements.
Positional embeddings converted from FP32 to FP16 to further reduce model size while retaining higher precision than the quantized vision layers.
These optimizations reduce the mmproj-BF16 file size to approximately 20% of the original for the Q8_0, significantly lowering the storage requirements for on-device deployment.
license: gemma
- Created
- Sep 23, 2026
- Updated
- Oct 17, 2026