stepfun-ai/Step-3.7-Flash-NVFP4
Image-Text-to-Text • 104B • Updated • 53.4k • 42
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 about 9 hours ago
ubergarm/Kimi-K2.6-GGUF:Q4_X on Blackwell + EPYC + DDR 5 new activity about 9 hours ago
AesSedai/GLM-5.1-GGUF:MTP liked a model 2 days ago
stepfun-ai/Step-3.7-Flash-NVFP4Organizations
None yet
Q4_X on Blackwell + EPYC + DDR 5
👍🔥 4
7
#3 opened about 2 months ago
by sousekd
MTP
2
#2 opened 28 days ago
by 
RedDragonGecko
liked a
model 2 days ago
liked 2
models 4 days ago
Rambling nonsense
4
#3 opened 24 days ago
by sousekd
liked 2
models 23 days ago
Context Length for 2X6000 Pros (2x96 = 192GB VRAM)
3
#2 opened about 1 month ago
by 
mtcl
SGLang kernel version exception
#8 opened 24 days ago
by sousekd
liked a
model 24 days ago
Q5_K_M inference speed on llama.cpp vs ik_llama.cpp
❤️👍 2
#1 opened about 1 month ago
by sousekd
liked 4
models about 1 month ago
Great model for single GPU use cases.
🔥 4
16
#1 opened about 1 month ago
by 
phakio
liked 2
models about 1 month ago
No think tags.
10
#4 opened about 1 month ago
by 
DrRos