Llama.cpp's Q2_K quant is 2.5625 bpw with perplexity just barely better than the next step down: https://github.com/ggerganov/llama.cpp/pull/1684

But subjectively, the Q2 quant "feels" worse than its high wikitext perplexity would suggest.

That's apples to oranges, as this quantization is different than Q2_K, but I just hope the quality hit in practice isn't so bad.