Victor C.
dehnhaide
AI & ML interests
None yet
Recent Activity
new activity about 18 hours ago
unsloth/MiniMax-M2.7-GGUF:UD-Q4_K_XL of MiniMax-M2.7-GGUF in BROKEN liked a model 1 day ago
cyankiwi/MiniMax-M2.7-AWQ-4bit liked a model 1 day ago
NeuroSenko/MiniMax-M2.7-exl3Organizations
None yet
UD-Q4_K_XL of MiniMax-M2.7-GGUF in BROKEN
6
#5 opened 2 days ago
by
dehnhaide
GLM 5.1 vs GLM 5 - burns A LOT output tokens on thinking
๐ 1
31
#6 opened 4 days ago
by
curiouspp8
Question about benchmark results
๐ฅ๐ 2
8
#5 opened about 1 month ago
by
tarruda
Need a 5% and 15% REAP
7
#10 opened 3 days ago
by
nawoalanor
Hoping for your magic on MiniMax-M2.7-FP8-INT4-AWQ quant
10
#2 opened 3 days ago
by
dehnhaide
GGUF quants available โ all sizes Q2_K through Q8_0 + BF16
๐โค๏ธ 1
2
#8 opened 3 days ago
by
dennny123
I'm on waiting list for AesSedai Minimax M2.7 Q4_K_M or similar...
โค๏ธ 1
4
#3 opened 27 days ago
by
MartinPatterson
Testing smol-IQ5_KS
4
#13 opened 5 days ago
by
shewin
Model seems to have issues in vLLM (characters duplication)
๐ฅ 1
8
#15 opened 12 days ago
by
dehnhaide
Check out Thireus GGUF-Tool-Suite quants!
โค๏ธ๐ค 5
8
#13 opened 11 days ago
by
ubergarm
Quant HAS issues + results with vLLM on 8x 3090
4
#1 opened 12 days ago
by
dehnhaide
accuracy
26
#4 opened about 2 months ago
by
ktsaou
Offloading layers is not working for me
9
#9 opened 22 days ago
by
tnuvkeg
AesSedai/Kimi-K2.5-GGUF using the Q4_X on 8 RTX 3090
๐ 1
12
#7 opened 18 days ago
by
martossien
The RTX3090 works very well๏ผths๏ผ
โค๏ธ๐ 4
3
#2 opened 29 days ago
by
summerbuild
Yet another excellent quant suite from AesSedai
#1 opened 20 days ago
by
dehnhaide
Tool calling
7
#1 opened 25 days ago
by
dehnhaide
duplicated tensor files
2
#1 opened 28 days ago
by
ak1020
Performance indicators
๐ 2
4
#1 opened 22 days ago
by
dehnhaide