Gemma 4 31B
Google DeepMindwe engineered a custom mobile-quantization schema designed for edge hardware
1 more from this model
mobile quantization: per-channel low bitwidth weight (mix of int2 and int4) and activation quantization (int8).
specific method · filed under inference & serving
Mobile quantization is an inference-quantization schema engineered for mobile and edge hardware.1 It pre-calculates activation scaling during training, quantizes channel-wise to match mobile accelerators, and compresses token-generating parts more aggressively while keeping core layers at higher precision.2
Trade-off It saves storage and memory without degrading the model's quality.3
Summarised by glm-5.3-flash from 1 source; every sentence is checked against the quote it cites.
we engineered a custom mobile-quantization schema designed for edge hardware— Gemma 4 QAT models: Optimizing model compression for mobile and laptop efficiency
Static activations: Normally, models waste processing power calculating how to scale data on the fly. We pre-calculate these settings during training— Gemma 4 QAT models: Optimizing model compression for mobile and laptop efficiency
This saves storage without making the model less smart— Gemma 4 QAT models: Optimizing model compression for mobile and laptop efficiency
Also called mobile-specialized quantization schema, custom mobile-quantization schema.
2 quotes from 2 sources, one card per model, each opening with its strongest.
we engineered a custom mobile-quantization schema designed for edge hardware
mobile quantization: per-channel low bitwidth weight (mix of int2 and int4) and activation quantization (int8).