BREAKING
Apple Eyes PrismML 1-Bit Tech
0
B
parameters
0
GB
memory use
0
x
size reduction
Memory Footprint by Model
Bonsai 8B
1.15
Bonsai 4B
0.5
Bonsai 1.7B
0.24
0
benchmark avg
0
GSM8K
0
HumanEval+
Native 1-Bit vs Conventional AI
PrismML 1-bit
native
●
Weights are +1 or -1
●
No high-precision layers
●
Apache 2.0, runs on MLX
Conventional
FP16
●
8B model needs ~16GB
●
Hard to fit on edge
●
Often needs the cloud
On-Device AI Talks in Play
AI NEWS BLITZ
Apple is in talks with startup PrismML to run big AI models directly on iPhones.