sakamakismile/Qwen3.6-27B-Text-NVFP4-MTP
Text Generation • 17B • Updated • 778k • 58
David Soušek
sousekd
AI & ML interests
Running AI on-prem with agents processing confidential data. Supporting government, private sector, and all kinds of weirdos.
Recent Activity
new activity 9 days ago
AesSedai/MiMo-V2.5-Pro-GGUF:Rambling nonsense liked a model 11 days ago
sakamakismile/Qwen3.6-27B-Text-NVFP4-MTP liked a model 12 days ago
poolside/Laguna-XS.2Organizations
None yet
Rambling nonsense
4
#3 opened 12 days ago
by sousekd
liked a
model 11 days ago
liked a
model 12 days ago
Context Length for 2X6000 Pros (2x96 = 192GB VRAM)
3
#2 opened 30 days ago
by 
mtcl
SGLang kernel version exception
#8 opened 12 days ago
by sousekd
liked a
model 13 days ago
Q5_K_M inference speed on llama.cpp vs ik_llama.cpp
👍❤️ 2
#1 opened 20 days ago
by sousekd
liked 2
models 20 days ago
liked a
model 21 days ago
liked a
model 24 days ago
Great model for single GPU use cases.
🔥 4
16
#1 opened 30 days ago
by 
phakio
liked 2
models about 1 month ago
No think tags.
10
#4 opened about 1 month ago
by 
DrRos
Q4_X on Blackwell + EPYC + DDR 5
👍🔥 4
6
#3 opened about 1 month ago
by sousekd
Working configuration for Nvidia Blackwell
13
#4 opened about 1 month ago
by 
luismiguelsaez
The Best Kimi Quant!
🔥 4
13
#1 opened about 1 month ago
by 
anikifoss
liked 2
models about 1 month ago
