HermiHg/Qwen3.8-27B-DFlash2-Q2_K_S-MIX-GGUF
Text Generation β’ 2B β’ Updated β’ 4.14k β’ 12
π ... it's amazing!
Schestex
Schestex
Β·
AI & ML interests
None yet
Recent Activity
new activity 1 day ago
cdiamond/Qwen3.8-27B-iMatrix-NVFP4-MTP-GGUF:MTP VS DFlash2 liked a model 2 days ago
HermiHg/Qwen3.8-27B-DFlash2-Q2_K_S-MIX-GGUFOrganizations
None yet
MTP VS DFlash2
1
#3 opened 3 days ago
by Schestex
liked a
model 2 days ago
reacted to OppaAI's post with π 3 days ago
Post
2597
Congrat to HuggingFace Team
https://techcrunch.com/2026/08/26/nvidia-closes-in-on-hugging-face-acquisition/
https://techcrunch.com/2026/08/26/nvidia-closes-in-on-hugging-face-acquisition/
- 3 replies
liked a
model 3 days ago
Why the NVFP4 MTP head beats a higher precision one (measured)
2
#1 opened 13 days ago
by 
cdiamond
liked a
model 7 days ago
VERSION NVFP4 : Qwen3.8-27B-Cold-Fusion-GAIN-V1.1-NVFP4
π 2
10
#13 opened 12 days ago
by Schestex
liked a
model 10 days ago
liked 5
models 11 days ago
cdiamond/Qwen3.8-27B-iMatrix-NVFP4-MTP-GGUF
Image-Text-to-Text β’ 0.5B β’ Updated β’ 609k β’ 7
maldv/Qwen3.6-27B-Isometry-Terse
Image-Text-to-Text β’ 28B β’ Updated β’ 108 β’ 3
signsur4739379373/Qwen3.6-27B-ThinkingCap-LoRA
Image-Text-to-Text β’ 35.3M β’ Updated β’ 49 β’ 1
Moore2877/Qwen-Fixed-Chat-Templates-llamacpp
Updated β’ 44
OBLITERATUS/Qwen3.8-27B-OBLITERATED
Text Generation β’ 28B β’ Updated β’ 726k β’ β’ 951
NVFP4-MTP build available for each model type?
3
#4 opened 12 days ago
by Schestex
liked 2
models 12 days ago
reacted to DavidAU's post with π 12 days ago
Post
14018
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
liked 2
models 12 days ago
