Minimax H3 INT8/INT4 Convrot Just uploaded both FL2VA &amp; REF2VA w4a8_mixed models quantized by Kijai. True int4 model size with int8 activations, near int8 quality, same speed as int8. For RAM-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. 14.81 GB INT4BQ Balanced-Quality leaning: int8_ratio 0.41 by count, 0.47 by params; int8mm_ratio 0.5817.27 GB INT4Q Quality: int8_ratio 0.73 by count, 0.75 by params; int8mm_ratio 0.27

Minimax H3 INT8/INT4 ConvRot

minimax_h3_ref2va_int8_convrot.safetensors

minimax_h3_fl2va_pruned_int8_convrot.safetensors

minimaxH3INT8INT4_fl2vaINT8Pruned.json

minimaxH3INT8INT4_fl2vaINT8Pruned.safetensors

minimax_h3_fl2va_bf16.safetensors

minimax_h3_video_vae_fp16.safetensors

minimax_h3_ref2va_bf16.safetensors

minimax_h3_audio_vae_fp32.safetensors

minimaxH3INT8INT4_fl2vaINT8Pruned_txt.safetensors

FL2VA INT8 Pruned

REF2VA INT4BQ Pruned

REF2VA INT4Q Pruned

FL2VA INT4Q Pruned

FL2VA INT4BQ Pruned

REF2VA INT8 Pruned

Files with SHA256: 9eef934046a0671bc8a5daf87100705e1478419c574cfde70c50fbe6885f76a9