Johannes Uusikuu

Johneeee

AI & ML interests

Small omlx models without vision & mtp for m1 m2 or low memory macs. Try the AURA quants. oQ5e aura6 is the sweet spot. They have PrismAura style sensitivity tensor bumps.

Recent Activity

new activity 3 days ago

DavidAU/Qwen3.8-27B-TWIN-TURBO-Fable-Cold-Fusion-709-L-Uncensored:PrismAura inspired quantifization brewing oQ4e plus oQ5e based bit bump quants with/without mtp, vision fp16,bf16

new activity 3 days ago

DavidAU/Qwen3.8-27B-TWIN-TURBO-Fable-Cold-Fusion-709-ULTRA-HERETIC-Uncensored:PrismAura NVFP4 quantifization

updated a model 5 days ago

Johneeee/Qwen3.8-27B-TWIN-TURBO-f-c-f-709-l-unc-oQ5e-aura6-last4-fp16-vision

View all activity

Organizations

None yet

Johneeee 's datasets

None public yet