Mindy

KungFuC1

AI & ML interests

None yet

Recent Activity

liked a Space 5 days ago

amphibiousrizz/Browser

liked a model 15 days ago

realrebelai/LOW_VRAM_Workflows

liked a model 21 days ago

Nimbz/Gemma-4-Dark-Gemistry-31B

View all activity

Organizations

None yet

liked a Space 5 days ago

AmphibiousRizz LoRA Browser

🐸

Visual browser for amphibiousrizz's Krea 2 character LoRAs

liked a model 15 days ago

realrebelai/LOW_VRAM_Workflows

Text-to-Image • Updated 3 days ago • 58

liked 3 models 21 days ago

liked a model 24 days ago

UltimateIntent/Gemory-26B-A4B-GGUF

Text Generation • 25B • Updated 24 days ago • 28.2k • 29

liked 2 models 26 days ago

zerofata/G4-MeroMero-v2-31B

31B • Updated Aug 3 • 2.38k • 75

ReadyArt/gemma-4-31B-it-scotoma-2-GGUF

Text Generation • 31B • Updated Aug 6 • 265k • 38

liked a model 27 days ago

ReadyArt/Serenity-27B-GGUF

27B • Updated Aug 27 • 4.22k • 10

liked a model about 1 month ago

samuel-vitorino/sopro-v2-turbo

Text-to-Speech • 0.1B • Updated 29 days ago • 24.3k • 32

reacted to DavidAU's post with 👍 about 1 month ago

Post

22611

Qwen3.8 - 27B - COLD FUSION

Reduction in thinking tokens to 1/10 to 1/2 "normal Qwen" across all three modes of thinking without loss of detail in thinking or output.

Increase in general intelligence too (all 7 critical benches); bench marks posted.

Trained using the COLD FUSION method (GAIN + UNSLOTH).
NOTE: This is NOT a heretic / uncensored version.

MTP and GGUF NEO MAX quants:
DavidAU/Qwen3.8-27B-Cold-Fusion-GAIN-V1.1-NM-DAU-NEO-MAX-MTP-GGUF

SOURCE:
DavidAU/Qwen3.8-27B-Cold-Fusion-GAIN-V1.1