Jay
Abiray
AI & ML interests
None yet
Recent Activity
updated a model 6 days ago
Abiray/10Eros-Max-ref2va-Beta2-GGUF published a model 6 days ago
Abiray/10Eros-Max-ref2va-Beta2-GGUFOrganizations
Settings and strength for minimax_h3_turbo_4step_ckpt600_ema_V4.safetensors
3
#5 opened 1 day ago
by
necroryona
GGUf for text encoder?
1
#1 opened 10 days ago
by
ryg81
V2V and First_Middle_Last_Frame
1
#4 opened 11 days ago
by
Oscarlau
qwen3vl_32b_minimax_h3_int4_convrot.safetensors can't be loaded due to 85 bytes of trailing data
1
#19 opened 14 days ago
by
jmillikin
INT4_INT8 model produces voice-over instead of character lip-sync
2
#18 opened 15 days ago
by
wsq194
How was pruning done and how was the performance loss evaluated?
2
#2 opened 17 days ago
by
Jerrisk
workflows?
1
#2 opened 17 days ago
by
loscrossos
Its working with old vae, TE, but i s that OK?
4
#1 opened 17 days ago
by
ryg81
MiniMax-h3?
1
#1 opened 19 days ago
by
davoodkharmanzar
ERROR qwen3vl_32b_minimax_h3_int4_convrot.safetensors is malformed
3
#15 opened 19 days ago
by
CoolSpot
Q2_K_M version??
1
#1 opened 20 days ago
by
davoodkharmanzar
Q6?
1
#9 opened 21 days ago
by
MrSanders13
Very Sharp Results ??
5
#2 opened 23 days ago
by
davoodkharmanzar
Pruned version?
4
#3 opened 26 days ago
by
stfred
I want even faster
3
#3 opened 22 days ago
by
Kidly
Thanks! Any chance of pruned MXFP8 versions for Blackwell?
2
#13 opened 22 days ago
by
1ikhan
How to run it with sglang and vvlm and diffusion studio
1
#12 opened 23 days ago
by
Msaadakram