Aes Sedai PRO
AesSedai
AI & ML interests
None yet
Recent Activity
new activity 1 day ago
AesSedai/Qwen3.5-397B-A17B-GGUF:Bad name? updated a model 1 day ago
AesSedai/Qwen3.5-397B-A17B-GGUF liked a model 4 days ago
lukealonso/GLM-5.2-NVFP4Organizations
Bad name?
3
#12 opened 3 days ago
by
qenme
Failed to initialize samplers: failed to parse grammar.
12
#2 opened 6 days ago
by
Exostyle81
Any chance of Q8?
4
#1 opened 6 days ago
by
MB7977
βThe doom lies in yourself, not in your name.β
π 7
537
#15 opened 11 months ago
by
jukofyork
PPQ(Q)/PPL(base) and KLD seems significantly worse than Step 3.5 Flash
π 1
23
#2 opened 2 months ago
by
tarruda
Thanks for the quick quants! Reccomended mmproj?
2
#1 opened about 2 months ago
by
phakio
Kimi 2.7 GGUF?
1
#2 opened about 2 months ago
by
ChuckMcSneed
Nex-N2-Pro
1
#11 opened about 2 months ago
by
sousekd
MTP
4
#2 opened 3 months ago
by
RedDragonGecko
Quants With MTP
9
#5 opened 4 months ago
by
tnhnyzc
New upload taking more VRAM with MTP disabled?
4
#4 opened 2 months ago
by
grumd0
Problems....
9
#3 opened 2 months ago
by
Nerdsking
Step-3.5 Flash Midtrain GGUF
5
#6 opened 2 months ago
by
Anaya3D
what llama.cpp fork can the IQ4_XS model be run? stepfun's fork is not working.
4
#1 opened 2 months ago
by
rosspanda0
KLD Files
1
#13 opened 2 months ago
by
Downtown-Case
MTP support merged in llama.cpp
13
#10 opened 3 months ago
by
tarruda
MTP support?
π 1
8
#5 opened 3 months ago
by
Nindaleth
Rambling nonsense
4
#3 opened 3 months ago
by
sousekd
Any llama.cpp parameters to work around the looping?
π 1
2
#12 opened 3 months ago
by
tarruda