AbstractFramework
/

wan2.2-t2v-a14b-diffusers-8bit

8-bit precision

video-generation

Model card Files Files and versions

lpalbou commited on 4 days ago

Commit

177422b

·

verified ·

1 Parent(s): 358f022

Round validation table values

Files changed (1) hide show

README.md +3 -3

README.md CHANGED Viewed

@@ -53,9 +53,9 @@ Bottom line:
 | Layout | Disk | MLX Peak | Physical Peak | Time | Result |
 | --- | ---: | ---: | ---: | ---: | --- |
-| Original source snapshot | 118 GiB | 32.99 GiB | 48.90 GiB | 108.31 s | Baseline. |
-| BF16 package | 64 GiB | 32.98 GiB | 45.12 GiB | 114.39 s | Storage only; output was byte-identical. |
-| This mixed q8/BF16 package | 40 GiB | 20.84 GiB | 31.75 GiB | 110.34 s | Storage and memory; side-by-side quality validation passed. |
 Compared with the original source snapshot, this mixed q8/BF16 package cuts disk usage by about 66%, MLX peak memory by about 37%, and physical peak memory by about 35% in this validation run. It is not byte-identical to BF16, but the validation contact sheet stayed in the same visual family. The prepared q8/BF16 output was byte-identical to running `--quantize 8` from the upstream source snapshot.

 | Layout | Disk | MLX Peak | Physical Peak | Time | Result |
 | --- | ---: | ---: | ---: | ---: | --- |
+| Original source snapshot | 118 GiB | 33.0 GiB | 48.9 GiB | 108.3 s | Baseline. |
+| BF16 package | 64 GiB | 33.0 GiB | 45.1 GiB | 114.4 s | Storage only; output was byte-identical. |
+| This mixed q8/BF16 package | 40 GiB | 20.8 GiB | 31.8 GiB | 110.3 s | Storage and memory; side-by-side quality validation passed. |
 Compared with the original source snapshot, this mixed q8/BF16 package cuts disk usage by about 66%, MLX peak memory by about 37%, and physical peak memory by about 35% in this validation run. It is not byte-identical to BF16, but the validation contact sheet stayed in the same visual family. The prepared q8/BF16 output was byte-identical to running `--quantize 8` from the upstream source snapshot.