Update quantization.md (#1246) #3013

Job	Run time
torchchat-command-load-test (macos-14)	1m 29s
gather-models-cpu	14s
test-gguf-util (macos-14)	4m 14s
test-mps (macos-m1-stable)	59s
gather-models-gpu	13s
test-tinystories-executorch (16-core-ubuntu)	19m 38s
compile-gguf (macos-14)	5m 40s
test-tinystories-executorch (macos-14-xlarge)	17m 28s
runner-et (16-core-ubuntu)	7m 11s
runner-et (macos-14-xlarge)	4m 57s
runner-aoti (16-core-ubuntu)	4m 36s
runner-aoti (macos-14-xlarge)	3m 6s
test-mps-dtype (macos-m1-stable)	1m 49s
test-torchao-experimental (macos-14-xlarge)	5m 45s
test-build-runner-et-android / linux-job	12m 27s
test-cpu-compile (x86_64, stories15M)	16m 21s
test-cpu-eval-sanity-check (x86_64, stories15M)	9m 31s
test-cpu-compile (aarch64, stories15M)	11m 32s
test-cpu-aoti (x86_64, stories15M)	16m 41s
test-cpu-eval-sanity-check (aarch64, stories15M)	9m 27s
test-cpu-aoti (aarch64, stories15M)	9m 53s
test-cpu-eval-sanity-check-float16 (x86_64, stories15M)	29m 5s
test-cpu-eval-sanity-check-float32 (x86_64, stories15M)	36m 46s
test-cpu-eval-sanity-check-float16 (aarch64, stories15M)	6m 51s
test-cpu-eval-sanity-check-float32 (aarch64, stories15M)	10m 16s
test-gpu-aoti-bfloat16 (cuda, stories15M) / linux-job	13m 19s
test-gpu-aoti-float16 (cuda, stories15M) / linux-job	12m 51s
test-gpu-aoti-float32 (cuda, stories15M) / linux-job	12m 14s
test-gpu-compile (cuda, stories15M) / linux-job	23m 24s
test-gpu-eval-sanity-check (cuda, stories15M) / linux-job	11m 9s
	5h 19m 6s

Provide feedback