Leonther/moe-40b-a18b-q4
Updated
Bao
Leonther
·
AI & ML interests
None yet
Recent Activity
published a model about 20 hours ago
Leonther/moe-40b-a18b-q4 updated a model about 20 hours ago
Leonther/moe-40b-a18b-lora published a model about 21 hours ago
Leonther/moe-40b-a18b-loraOrganizations
published a
model about 20 hours ago
updated a
model about 20 hours ago
published a
model about 21 hours ago
updated a
dataset about 21 hours ago
published a
dataset about 21 hours ago
amazing model, i tested it for degradation in vision but same level as as base qwen3.8 27b on my tests, exactly the same level, amazing otherwise even with advanced browseruse
reacted to DavidAU's post with 🤝 about 1 month ago
Post
22463
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
Is this possible?
👍👀 2
2
#9 opened about 1 month ago
by 
PunitN
liked a
model about 1 month ago
liked a
model about 2 months ago
