Downloads · 30 days
0
MiniMax-H3-experimental
Kijai/MiniMax-H3-experimental
MiniMax-H3-experimental is a machine learning model from Kijai. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
w4a8 is a format using 4-bit weights and int8-convrot activations
Access
Public
Updated Sep 29, 2026
Repo size
114 GB
Likes
515
Trending 27
Repo makeup
Click a slice to open those files.
.safetensors100 GB · 100%
At a glance
- Access
- Public
- Created
- Aug 5, 2026
- Updated
- Sep 29, 2026
- SHA
- a32d8b8b
Model card
From the Hugging Face model README
w4a8 is a format using 4-bit weights and int8-convrot activations
Requires ComfyUI 0.31.0
int8_convrot VAE needs ComfyUI 0.36.0 for maximum speed benefit
It speeds up VAE decode times by ~2x
ref lora is the difference between fl2va and ref2va, completely experimental, I don't even know if it has a use case at this point.
w6a8 is a format using 6-bit weights and int8-convrot activation, work in progress
minimax_h3_ref2va_pruned_w6a8_g32.safetensor
- Created
- Aug 5, 2026
- Updated
- Sep 29, 2026