Sign In
homemodelsimagesvideos3D Modelshubsarticlescomicschallengesupdatesshop

Minimax H3 INT8/INT4 ConvRot

Updated: Aug 17, 2026

base model

Download

1 variant available

int8 SafeTensor

minimax_h3_fl2va_pruned_int8_convrot.safetensors

8-bit integer, smaller file • 19.53 GB

Verified:

You need these files to run this model. We'll show the best match for your preferences.

Minimax
VAE

H3 (Comfy) • minimax_h3_audio_vae_fp32.safetensors

577.22 MB

Minimax
VAE

H3 (Comfy) • minimax_h3_video_vae_fp16.safetensors

4.85 GB

Minimax
CLIP Vision

H3 (Comfy) • qwen3vl_32b_minimax_h3_nvfp4_awq.safetensors

14.61 GB

Downloads your preferred variants

Type
Checkpoint
Stats

21,005

578

Reviews

(1,389)

Published

Aug 3, 2026

Base Model

MiniMax H3

Hash
AutoV2
E889202C41
default creator card background decoration

#2

Followers - 846

846

License:

MiniMax H3 Community License Agreement

MiniMax H3 is licensed by MiniMax under the MiniMax H3 Community License Agreement. That agreement’s Applicable Territory excludes the European Union, the United Kingdom, the Republic of Korea and the United States of America. Your use of H3 and of any H3 derivative is subject to that agreement and its Acceptable Use Policy.

MiniMax H3

Minimax H3 INT8/INT4 Convrot

Just uploaded both FL2VA & REF2VA w4a8_mixed models quantized by Kijai. (Makes my mixed int4 models obsolete) True int4 model size with int8 activations, near int8 quality, same speed as int8. For RAM/VRAM-constrained systems. Update your ComfyUI to the latest version for support of the new w4a8 (Should be included in Stable ComfyUI v0.31.0 https://github.com/Comfy-Org/ComfyUI/pull/15308

FL2VA - first last (frame) to video / audio
REF2VA - ref_images / ref_videos / ref_video_audios / ref_audios: up to 9 reference images, 3 reference videos (each may carry its own paired soundtrack), and 3 standalone reference audio clips

Both models can generate t2v (Text to video), i2v (Image to video), v2v (Video to Video), a2v (Audio to video), and multiple references (image/video/audio). But were further fine-tuned/trained for higher-quality outputs for the intended use.