Aaron Newsome
aaron-newsome
AI & ML interests
None yet
Recent Activity
new activity 3 days ago
deepseek-ai/DeepSeek-V4-Flash-0731:How can it be served with 4 x RTX Pro6000? liked a model 6 days ago
MiniMaxAI/MiniMax-H3 new activity 9 days ago
deepseek-ai/DeepSeek-V4-Flash-0731:Going completely madOrganizations
None yet
How can it be served with 4 x RTX Pro6000?
👀 1
16
#22 opened 9 days ago
by
niuchuang
Going completely mad
🚀🔥 45
11
#1 opened 9 days ago
by
xiezirock
absolutely fantastic on 4x RTX PRO 6000
❤️🔥 6
16
#1 opened 29 days ago
by
aaron-newsome
Beware of the kv_cache params!
🔥😔 7
19
#36 opened 21 days ago
by
aaron-newsome
Will it fit in 2X6K Pros?
👍 1
12
#1 opened about 1 month ago
by
mtcl
How to run on 4x RTX PRO 6000 Blackwell 96GB (SM120)
20
#1 opened about 2 months ago
by
aaron-newsome
How To Run on 4x RTX 6000 PRO Blackwell (SM120)
9
#1 opened about 2 months ago
by
aaron-newsome
Proposal for the Ultimate Local SOTA:
1
#2 opened 3 months ago
by
netforcetech
512 GB + 24-44 Vram option
👍 1
1
#6 opened 4 months ago
by
DiegoVSulz
FANTASTICAL and much appreciated!
#2 opened 3 months ago
by
aaron-newsome
Grok 3 release time?
➕ 3
6
#44 opened 7 months ago
by
ZeroWw
Thanks, thanks and more thanks. Many thanks.
15
#2 opened 4 months ago
by
aaron-newsome
Working configuration for Nvidia Blackwell
13
#4 opened 4 months ago
by
luismiguelsaez
very fast!!!
❤️🤗 1
5
#2 opened 6 months ago
by
rosspanda0
Core dumped for me,
7
#3 opened 6 months ago
by
aaron-newsome
How to enable vision encoder?
1
#10 opened 6 months ago
by
stefan28123
Q3_K_XL works surprisingly fast for 3x3090 + 128 ram
🔥 8
7
#4 opened 6 months ago
by
fizzacles
Chat template issues with newer llama.cpp?
#9 opened 6 months ago
by
aaron-newsome
Question : Real-world use cases for Step-3.5-Flash
8
#24 opened 6 months ago
by
Geodd
Hot Damn This Model Cooks!
👍 6
12
#5 opened 7 months ago
by
aaron-newsome