B E
Smite79
AI & ML interests
None yet
Recent Activity
new activity 25 minutes ago
joeygambino/MiniMax-H3-Multishot-Workflow:Option to make it work with 4 step Lora? new activity 42 minutes ago
joeygambino/MiniMax-H3-encoder-GGUF:state_dict mismatch between the mmproj and the Q5_K_M GGUF liked a model about 16 hours ago
DmitryDB/MiniMax-H3-ComfyUI-QuantsOrganizations
None yet
Option to make it work with 4 step Lora?
1
#2 opened about 7 hours ago
by
GeoSt77
state_dict mismatch between the mmproj and the Q5_K_M GGUF
5
#1 opened about 13 hours ago
by
Smite79
NVFP4 W4A4 Quantized?
#2 opened about 16 hours ago
by
Smite79
Awesome performance on an RTX 5060 Ti!
#1 opened about 18 hours ago
by
Smite79
Not working - blows errors
1
#1 opened 1 day ago
by
Smite79
not abliterated
5
#10 opened 1 day ago
by
rzgar
Speedup 4-step LoRa ?
👀➕ 18
8
#11 opened 4 days ago
by
joziku
Please release an INT4-quantized version of MiniMax-H3
👍 3
9
#22 opened 3 days ago
by
makisekurisu-jp
Approximating VAE? (Or video preview in general)
9
#20 opened 4 days ago
by
inflatebot
Will there be FP8 and NVFP4 of the models?
13
#5 opened 4 days ago
by
VivekThePreceptor
the only thing i can say , LTX2.3 is like trash next to H3
👍 6
11
#8 opened 4 days ago
by
agapes
Why it gives me OOM with 21gb gguf model but gens fine with 27gb fp8 safetensor?
👍 1
1
#12 opened 5 months ago
by
Zuzuus
ltx 2.3 distilled nvfp4
👀 2
2
#10 opened 22 days ago
by
famirsh
Any ETA for the Next Version or LTX2.5 ?
2
#61 opened 29 days ago
by
FP128765
F8_E8M0 error
#1 opened 19 days ago
by
Smite79
LTX TILE SAMPLER need to offload vram after first step
👍 1
2
#6 opened about 1 month ago
by
joffreypersonal
Is there any way to speed up the generation?
5
#6 opened 22 days ago
by
soxon
Is the 8step lora trained by DMD2?
1
#68 opened 29 days ago
by
idealwhite
Please support INT8 Model loader for x2 Speed boost
👀➕ 9
10
#62 opened 3 months ago
by
AndyDev92