🔆 Thinking....
Cosmic Nag
cosmicnag
AI & ML interests
None yet
Recent Activity
liked a model 2 days ago
MirkoCovizzi/Qwen3.8-27B-QUASAR-NVFP4-NInfer liked a model 3 days ago
QUASAR-QAT/Qwen3.8-27B-QUASAR-NVFP4 liked a model 3 days ago
Qwen/Qwen3.8-Flash-NextOrganizations
None yet
Linux/SGLang/LMHead4/TextOnly/DSpark/236k context single 5090 GODSPEED recipe
❤️ 2
#1 opened 8 days ago
by
cosmicnag
Linux/SGLang/LMHead4/DSpark/TextOnly/236k context single 5090 GODSPEED recipe
#11 opened 8 days ago
by
cosmicnag
Qwen 3.8 + DSpark + vLLM
👀 2
2
#9 opened 9 days ago
by
gittyeric
Text-only / MTP3 / native-262k RTX-5090 profile
👍 1
1
#1 opened 10 days ago
by
cosmicnag
RTX 5090 viabiliity
#1 opened 11 days ago
by
cosmicnag
No model file in repo / still uploading ?
2
#1 opened 11 days ago
by
cosmicnag
Getting garbled text
10
#1 opened 13 days ago
by
cosmicnag
New activity in DavidAU/Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-NEO-MAX-MTP-GGUF 21 days ago
VERSION: PrismAura quantized version (DGX Spark optimized)
❤️👍 4
1
#70 opened 23 days ago
by
trithemius
New activity in DavidAU/Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-NEO-MAX-MTP-GGUF 27 days ago
Good intelligence, even with Q4 quantitative quantification
🧠👍 4
8
#5 opened about 1 month ago
by
Healy0
New activity in DavidAU/Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-NEO-MAX-MTP-GGUF about 1 month ago
NVFP4?
👀 2
23
#2 opened about 1 month ago
by
cosmicnag
any plan to release the full precision model?
🔥👍 5
29
#3 opened about 1 month ago
by
electroglyph
Recommended temperature and other settings?
3
#8 opened about 2 months ago
by
cosmicnag
Usage review
3
#10 opened about 2 months ago
by
SRZhu26
Qwen3.6-27B-NVFP4?
🔥➕ 17
14
#6 opened 3 months ago
by
YanTianlong