Minimax H3 INT8/INT4 Convrot Required Components added to description as the files link to the official Civitai Minimax H3 model page which is set to generation-only, with no option to unlink. <a rel="ugc" href="https://huggingface.co/Comfy-Org/MiniMax-H3/resolve/main/text_encoders/qwen3vl_32b_minimax_h3_nvfp4_awq.safetensors">text_encoders/qwen3vl_32b_minimax_h3_nvfp4_awq.safetensors</a> <a rel="ugc" href="https://huggingface.co/Comfy-Org/MiniMax-H3/resolve/main/vae/minimax_h3_audio_vae_fp32.safetensors">vae/minimax_h3_audio_vae_fp32.safetensors</a> <a rel="ugc" href="https://huggingface.co/Comfy-Org/MiniMax-H3/resolve/main/vae/minimax_h3_video_vae_fp16.safetensors">vae/minimax_h3_video_vae_fp16.safetensors</a> Just uploaded both FL2VA &amp; 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 <a target="_blank" rel="ugc" href="https://github.com/Comfy-Org/ComfyUI/pull/15308">https://github.com/Comfy-Org/ComfyUI/pull/15308</a> 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.

Minimax H3 INT8/INT4 ConvRot

True int4 model size with int8 activations, near int8 quality same speed as int8. For ram contsrained systems

Files with SHA256: 4a58d435974fa98089b471fbb70e582656f34b86b5f1fad630b8de3c81eb5628