--- title: MiniMax-H3-INT8-CONVROT canonical_url: "https://www.modelscope.cn/models/Gluttony10/MiniMax-H3-INT8-CONVROT" md_url: "https://www.modelscope.cn/models/Gluttony10/MiniMax-H3-INT8-CONVROT.md" repository: Gluttony10/MiniMax-H3-INT8-CONVROT last_updated: 2026-08-28 license: other base_model: - MiniMaxAI/MiniMax-H3 base_model_relation: finetune parameters: 97.5B tensor_type: - F32 - BF16 - I8 - U8 - F16 library_name: - safetensors downloads: 18707 stars: 15 tags: - comfyui - text-to-video - image-to-video - audio-video-generation - multimodal - int8 --- # MiniMax-H3-INT8-CONVROT > MiniMax-H3-INT8-CONVROT - Gluttony10 在 ModelScope 开源的模型。MiniMax-H3 INT8 ConvRot Gluttony10/MiniMax-H3-INT8-CONVROT 是 ModelScope 魔搭社区上的 97.5B 参数机器学习模型，采用 other 许可，基于 MiniMaxAI/MiniMax-H3 构建。 - **Repository**: Gluttony10/MiniMax-H3-INT8-CONVROT - **License**: other - **Parameters**: 97.5B - **Base model**: MiniMaxAI/MiniMax-H3 - **Tags**: comfyui, text-to-video, image-to-video, audio-video-generation, multimodal, int8 - **Downloads**: 18707 - **Stars**: 15 - **Last updated**: 2026-08-28 Source: https://www.modelscope.cn/models/Gluttony10/MiniMax-H3-INT8-CONVROT --- # MiniMax-H3 INT8 ConvRot [简体中文](README_CN.md) Converted MiniMax-H3 weights for [ComfyUI-RH-MiniMax-H3](https://github.com/RH-RunningHub/ComfyUI-RH-MiniMax-H3). This repository is a complete ComfyUI bundle: INT8 ConvRot DiT / text-encoder weights, merged VAEs, FL2VA / Ref2VA configs, and optional turbo LoRAs. The same package is mirrored on [ModelScope](https://modelscope.cn/models/Gluttony10/MiniMax-H3-INT8-CONVROT). Download from **one** source. The full snapshot is about **99 GiB**; keep at least **120 GiB** free. ## Contents | File | Size | Role | |---|---:|---| | `MiniMax-H3-FL2VA-int8_convrot.safetensors` | 31.65 GiB | FL2VA / T2VA / V2A DiT | | `MiniMax-H3-Ref2VA-int8_convrot.safetensors` | 31.65 GiB | Ref2VA DiT | | `qwen3-vl-32b-int8_convrot.safetensors` | 25.28 GiB | Qwen3-VL text encoder | | `MiniMax-H3-video_vae.safetensors` | 4.85 GiB | Video VAE | | `MiniMax-H3-audio_vae.safetensors` | 0.56 GiB | Audio VAE | | `minimax_h3_fl2v_turbo_4step_v0.1.safetensors` | 1.29 GiB | Optional FL2VA / T2VA 4-step turbo | | `minimax_h3_fl2v_turbo_4step_v1.0_768p_bf16.safetensors` | 1.29 GiB | Optional FL2VA / T2VA 4-step turbo for 768p | | `minimax_h3_fl2v_turbo_8step_v1.0_bf16.safetensors` | 1.29 GiB | Optional FL2VA / T2VA 8-step turbo | | `minimax_h3_ref2v_turbo_4step_v0.1_bf16.safetensors` | 1.29 GiB | Optional Ref2VA 4-step turbo | | `FL2VA/` | configs | FL2VA tokenizer, processor, and component configs | | `Ref2VA/` | configs | Ref2VA tokenizer, processor, and component configs | ## Install into ComfyUI ```text ComfyUI/ └── models/ └── MiniMax-H3-INT8-CONVROT/ ├── MiniMax-H3-FL2VA-int8_convrot.safetensors ├── MiniMax-H3-Ref2VA-int8_convrot.safetensors ├── qwen3-vl-32b-int8_convrot.safetensors ├── MiniMax-H3-video_vae.safetensors ├── MiniMax-H3-audio_vae.safetensors ├── minimax_h3_fl2v_turbo_4step_v0.1.safetensors ├── minimax_h3_fl2v_turbo_4step_v1.0_768p_bf16.safetensors ├── minimax_h3_fl2v_turbo_8step_v1.0_bf16.safetensors ├── minimax_h3_ref2v_turbo_4step_v0.1_bf16.safetensors ├── FL2VA/ └── Ref2VA/ ``` ```bash cd /path/to/ComfyUI python3 -m pip install -U huggingface_hub hf download Gluttony10/MiniMax-H3-INT8-CONVROT \ --local-dir ./models/MiniMax-H3-INT8-CONVROT ``` China users can use the ModelScope mirror: ```bash cd /path/to/ComfyUI python3 -m pip install -U modelscope modelscope download --model Gluttony10/MiniMax-H3-INT8-CONVROT \ --local_dir ./models/MiniMax-H3-INT8-CONVROT ``` Re-run the same command to resume or update an interrupted download. On a high-bandwidth machine with at least 64 GiB RAM, prefix `hf download` with `HF_XET_HIGH_PERFORMANCE=1`. The plugin auto-detects this complete converted bundle. The legacy `ComfyUI/models/MiniMax-H3` directory remains supported. ## Optional Turbo LoRA Select one turbo LoRA in the model loader for fewer sampling steps. Leave the LoRA empty to run the base converted weights. | File | Typical use | |---|---| | `minimax_h3_fl2v_turbo_4step_v0.1.safetensors` | FL2VA / T2VA 4-step turbo | | `minimax_h3_fl2v_turbo_4step_v1.0_768p_bf16.safetensors` | FL2VA / T2VA 4-step turbo for 768p | | `minimax_h3_fl2v_turbo_8step_v1.0_bf16.safetensors` | FL2VA / T2VA 8-step turbo | | `minimax_h3_ref2v_turbo_4step_v0.1_bf16.safetensors` | Ref2VA 4-step turbo | ## Plugin Install [ComfyUI-RH-MiniMax-H3](https://github.com/RH-RunningHub/ComfyUI-RH-MiniMax-H3) and use the nodes under `RunningHub/MiniMax H3`: | Node | Purpose | |---|---| | `RHMiniMaxH3ModelLoader` | Load the FL2VA / Ref2VA DiT and optional LoRA | | `RHMiniMaxH3TextEncoderLoader` | Load the Qwen3-VL text encoder | | `RHMiniMaxH3VAELoader` | Load the video and audio VAEs | | `RHMiniMaxH3VideoGen` | T2VA / FL2VA / V2A | | `RHMiniMaxH3RefGen` | Ref2VA with ordered image, video, and audio references; audio-only is allowed | Example workflows: - [Text-to-video+audio](https://github.com/RH-RunningHub/ComfyUI-RH-MiniMax-H3/blob/main/examples/workflows/videogen_t2va.json) - [Video-to-audio](https://github.com/RH-RunningHub/ComfyUI-RH-MiniMax-H3/blob/main/examples/workflows/videogen_v2a.json) - [Image/audio reference generation](https://github.com/RH-RunningHub/ComfyUI-RH-MiniMax-H3/blob/main/examples/workflows/refgen_image_audio.json) ## License Converted weights follow the upstream [MiniMax-H3 Community License](https://huggingface.co/MiniMaxAI/MiniMax-H3/blob/main/LICENSE). The ComfyUI plugin code is Apache-2.0. ## Links - [ComfyUI-RH-MiniMax-H3](https://github.com/RH-RunningHub/ComfyUI-RH-MiniMax-H3) - [Official MiniMax-H3](https://github.com/MiniMax-AI/MiniMax-H3) - [Official MiniMax-H3 weights](https://huggingface.co/MiniMaxAI/MiniMax-H3) - [ModelScope mirror](https://modelscope.cn/models/Gluttony10/MiniMax-H3-INT8-CONVROT) - [RunningHub China](https://www.runninghub.cn/?inviteCode=rh-v1367) - [RunningHub International](https://www.runninghub.ai/?inviteCode=rh-v1367)