monster/modelbeast
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

benchmarks: Qwen-Layered ladder — 20 steps holds quality, 3.2x to 365.6s on m1ultra

Browse Source 
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
This commit is contained in:
m3ultra 2026-07-19 21:09:37 +10:00
parent 64afe54474
commit 0db2c90481
1 changed files with 13 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

13
BENCHMARKS.md
View File

@ -349,3 +349,16 @@ to the MESHGOD prep frontline for hero assets.
Optimization in progress: `mflux-save --quantize 8` pre-baked model →
skips load+quant cost; timed gen-only rerun to follow. Next: 1024-res,
q4/q6 quality ladder, m3ultra cross-bench.
### Qwen-Image-Layered optimization ladder (m1ultra, 640, q8, 4 layers)
| config | wall | note |
|---|---|---|
| cold: HF bf16 + on-the-fly q8, 50 steps | 1180.8 s | first smoke |
| baked q8 model, 50 steps | 1075.9 s | load cost was NOT dominant |
| **baked q8, 20 steps** | **365.6 s** | **quality held — figure cutout indistinguishable from 50-step. RECOMMENDED DEFAULT.** |
3.2× end-to-end. Peak 36.6GB. Baked model: ~/qwen-layered-staging/qwen-layered-q8 (34GB).
Remaining ladder (untested): q6/q4 quality/speed, 1024-res, fewer-steps floor (10?),
m3ultra cross-bench (~1.4× compute but needs 34GB disk — m3 disk currently tight),
MODELBEAST operator wrapper (qwen_layered_local) once defaults settle.