Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
gemma-4-12B-it-qat-oQ4e-fp16-mtp – AI Model by Grunzig | AlphaNeural AI
You can deploy this model and start earning money today!
Grunzig
/
gemma-4-12B-it-qat-oQ4e-fp16-mtp
like
0
mlx
safetensors
gemma4_unified
oq
quantized
omlx
fp16
apple-silicon
m1
m2
google/gemma-4-12B-it-qat-q4_0-unquantized
quantized
4-bit
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
gemma-4-12B-it-qat-oQ4e-fp16-mtp
This model was quantized using
oQ
(oMLX v0.6.3rc1) mixed-precision quantization.
google/gemma-4-12B-it-qat-q4_0-unquantized-assistant MTP head was merged into google/gemma-4-12B-it-qat-q4_0-unquantized.
It is optimized for Mac M1/M2 (fp16).
Quantization details
Model type
: gemma4_unified
Bits
: 4
Group size
: 64
Format
: MLX safetensors
Non-quant weight dtype
: FP16
