Add aider polyglot benchmark info and specific template

finally upload smol-IQ3_KS

uploading new recipe IQ3_K and update graph

uploading new IQ3_K and removing the old one

Update readme

add Q4_X notes as new baseline

upload Q4_X and add note before deleting Q8_0-Q4_0

add smol-IQ2_KL

Fixes the details closing tag (#12)

upload IQ2_KL which is looking good

Add -amb 512 option in quick start command notes

Add note to update chat template and use --special

update perplexity graph with full Q8_0 baseline

smol-IQ4_KSS looks good despite supposed q4_0 QAT

add perplexity graph as data completes

uploading smol-IQ1_KT for the desperate

uploading IQ3_K for the under 512GB crew

update example commands

add perplexity and stub out smol-IQ1_KT

fixup quant name lol

fixup ik_llama.cpp example command note

add rough quick start commands

Add 🫶

add references and more info almost done uploading

fixup readme

add model size 543.617 GiB (4.549 BPW)

testing quant fork ik and mainline