Gemma 3 0.27B 0.3B

User reports a paper replacing Gemma 3 270M's embedding table with a frozen 16 MB 512-bit code table, with a ternary BitNet b1.58 body giving a 46 MB model that generates 615 to 740 tokens per second on a laptop CPU in 62 MB of memory. The paper states this is five to six times the speed of the float model's 8-bit GGUF in llama.cpp at a seventh of the memory. The frozen table wins by 1.7 to 2.3 nats on rare words and accepts 10,000 new words after training at a 3% cost where the learned table collapses by 43%.