Amit Bhatnagar

bamit99

5 36

AI & ML interests

None yet

Recent Activity

liked a model 9 days ago

Qwen/Qwen3.8-Flash-Next

liked a model 22 days ago

Viggle/Qwen-Image-2.1-viggle-turbo

liked a model 24 days ago

Qwen/Qwen-Image-2.1

View all activity

Organizations

None yet

liked a model 9 days ago

Qwen/Qwen3.8-Flash-Next

Image-Text-to-Text • 180B • Updated Aug 27 • 2.19M • • 6.22k

liked a model 22 days ago

Viggle/Qwen-Image-2.1-viggle-turbo

Text-to-Image • 7B • Updated 14 days ago • 478k • 731

liked a model 24 days ago

Qwen/Qwen-Image-2.1

Text-to-Image • 7B • Updated 15 days ago • 154k • 3.31k

liked a model 27 days ago

atomtanstudio/lora-library

Text-to-Audio • Updated 9 days ago • 11

liked a model about 2 months ago

Qwen/Qwen-Image-Edit-2509

Image-to-Image • 20B • Updated Sep 22, 2025 • 464k • • 1.26k

reacted to DavidAU's post with 🔥 about 2 months ago

Post

22,763

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