ModelPublicadoExterno

MiniMax H3 Experimental

w4a8 is a format using 4-bit weights and int8-convrot activations

Fuentehuggingface.co/Kijai/MiniMax-H3-experimental/tree/d8023be02fefbb3633b0cd335c3879f91177299d

TipoModeloVersiónMinimax h3 4step lora flashgen v1.0 768p fl2va pruned avg rank 13 bf16

Fuente del modelo

Tipo: Modelo
Tamaño del archivo: 177 MB–21,3 GB
Versión: vMinimax h3 4step lora flashgen v1.0 768p fl2va pruned avg rank 13 bf16
Actualizado: 14 oct 2026
Fuente: Hugging Face

Descripción de la fuente

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

Fuentes

1 fuente

Hugging FacePrincipalVersión d8023be02fefbb3633b0cd335c3879f91177299d

huggingface.co/Kijai/MiniMax-H3-experimental/tree/d8023be02fefbb3633b0cd335c3879f91177299d

Verificado 14 oct

Artefactos del modelo

20 artefactos

loras/minimax_h3_4step_lora_flashgen_v1.0_768p_fl2va_pruned_avg_rank_13_bf16.safetensors

safetensors · 177 MB · SHA-256 1254d62240b1…b067 · Hugging Face

Descargar

loras/minimax_h3_DMAD_4step_full_lora_avg_rank_39_bf16.safetensors

safetensors · 350 MB · SHA-256 ddfdd94f4c9a…2d11 · Hugging Face

Descargar

Extractos de fuentes

2 extractos

Readme14 octhuggingface.co/Kijai/MiniMax-H3-experimental

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 https://github.com/Comfy-Org/comfy-kitchen/pull/191 --- ## minimax_h3_lynnreal_light_vae_int8_convrot.safetensors https://huggingface.co/stdstu123/LynnReal-Onmi-light-vae int8-convrot quant of the pruned light VAE, this is about 1.3x faster for decoding. --- ## PDMD loras Converted and rank reduced from: https://huggingface.co/pdmd2026/pdmd_2NFE_lora https://huggingface.co/pdmd2026/pdmd_4NFE_lora ## DMAD lora https://huggingface.co/ZhengmingYu/DMAD