FiditeNemini/MossForge
Updated โข 1
Fidite Nemini PRO
FiditeNemini
AI & ML interests
Prompt engineering, unalignment, MLX, model merging, diffusion models
Recent Activity
updated a model 2 days ago
FiditeNemini/MossForge published a model 6 days ago
FiditeNemini/MossForge updated a model 6 days ago
FiditeNemini/Qwen3.5-4B-thinking-mlx-8bitOrganizations
updated a
model 2 days ago
published a
model 6 days ago
updated a
model 6 days ago
published a
model 6 days ago
updated a
model 8 days ago
published a
model 8 days ago
liked a
model 15 days ago
Fantastic model - thank you!
๐ 2
2
#5 opened 15 days ago
by FiditeNemini
liked 2
models 16 days ago
updated a
model about 2 months ago
Quant request - MLX
#1 opened 2 months ago
by FiditeNemini
awesome work
๐ 2
2
#2 opened 2 months ago
by 
Salazarkzz
liked a
model 2 months ago
reacted to DavidAU's post with ๐ 2 months ago
Post
22,873
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
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
- 7 replies
published a
model 3 months ago
Extremely quick ttft
๐โค๏ธ 2
#13 opened 3 months ago
by FiditeNemini
liked 3
models 3 months ago
