gabe
gabriellarson
AI & ML interests
open source AI/ML - email: gabe@oct6.org
Organizations
None yet
llama.cpp support
1
#1 opened 5 months ago
by
engrtipusultan
Is MXFP4_MOE more efficient than Q4_K_M? Which one should perform better?
1
#3 opened 7 months ago
by
nmkd
Compatible with ollama?
5
#2 opened 7 months ago
by
Marioher
quant this pls
3
#1 opened 7 months ago
by
Utochi
Unable to GGUF quant: Errors out.
21
#2 opened 7 months ago
by
DavidAU
Converting to GGUF
2
#1 opened 7 months ago
by
gabriellarson
Is it normal that Q4 and Q8 are almost the same size as f16?
1
#2 opened 7 months ago
by
LiteSoulAI
what can run this?
3
#1 opened 7 months ago
by
csabakecskemeti
Question about Disclaimer
1
#1 opened 7 months ago
by
qingy2024
First!
❤️ 1
1
#1 opened 8 months ago
by
Fernanda24
Thanks for the mainline llama.cpp PR effort!
🔥 ❤️ 2
21
#1 opened 8 months ago
by
ubergarm
Add Github URL and library name
1
#1 opened 8 months ago
by
nielsr
Enderchef from ICONN AI
👍 1
1
#1 opened 8 months ago
by
Enderchef
Add link to code
2
#1 opened 9 months ago
by
nielsr
Is there any documentation about the sampling parameters maybe?
1
#1 opened 9 months ago
by
ljupco
How to run with mmproj
1
#1 opened 9 months ago
by
ShulgaSA