How do I run Minimax H3 on a Mac M3 Max? The official example doesn't work.

### Custom Node Testing

- [x] I have tried disabling custom nodes and the issue persists (see [how to disable custom nodes](https://docs.comfy.org/troubleshooting/custom-node-issues#step-1%3A-test-with-all-custom-nodes-disabled) if you need help)

### Your question

It's stuck at "loaded completely" for a long time, and there's no error message.

[video_minimax_h3_t2v.json](https://github.com/user-attachments/files/31600479/video_minimax_h3_t2v.json)

### Logs

```powershell
[INFO] setup plugin alembic.autogenerate.schemas
[INFO] setup plugin alembic.autogenerate.tables
[INFO] setup plugin alembic.autogenerate.types
[INFO] setup plugin alembic.autogenerate.constraints
[INFO] setup plugin alembic.autogenerate.defaults
[INFO] setup plugin alembic.autogenerate.comments
[WARNING] Could not autodetect AIMDO implementation, assuming Nvidia
[INFO] comfy-aimdo unsupported operating system: Darwin
[INFO] NOTE: comfy-aimdo currently only supports Windows and Linux
[INFO] Adding extra search path checkpoints /Users/jaxon/ComfyUI-Shared/models/checkpoints
[INFO] Adding extra search path classifiers /Users/jaxon/ComfyUI-Shared/models/classifiers
[INFO] Adding extra search path clip_vision /Users/jaxon/ComfyUI-Shared/models/clip_vision
[INFO] Adding extra search path configs /Users/jaxon/ComfyUI-Shared/models/configs
[INFO] Adding extra search path controlnet /Users/jaxon/ComfyUI-Shared/models/controlnet
[INFO] Adding extra search path controlnet /Users/jaxon/ComfyUI-Shared/models/t2i_adapter
[INFO] Adding extra search path diffusers /Users/jaxon/ComfyUI-Shared/models/diffusers
[INFO] Adding extra search path diffusion_models /Users/jaxon/ComfyUI-Shared/models/diffusion_models
[INFO] Adding extra search path embeddings /Users/jaxon/ComfyUI-Shared/models/embeddings
[INFO] Adding extra search path gligen /Users/jaxon/ComfyUI-Shared/models/gligen
[INFO] Adding extra search path hypernetworks /Users/jaxon/ComfyUI-Shared/models/hypernetworks
[INFO] Adding extra search path latent_upscale_models /Users/jaxon/ComfyUI-Shared/models/latent_upscale_models
[INFO] Adding extra search path loras /Users/jaxon/ComfyUI-Shared/models/loras
[INFO] Adding extra search path model_patches /Users/jaxon/ComfyUI-Shared/models/model_patches
[INFO] Adding extra search path audio_encoders /Users/jaxon/ComfyUI-Shared/models/audio_encoders
[INFO] Adding extra search path photomaker /Users/jaxon/ComfyUI-Shared/models/photomaker
[INFO] Adding extra search path style_models /Users/jaxon/ComfyUI-Shared/models/style_models
[INFO] Adding extra search path text_encoders /Users/jaxon/ComfyUI-Shared/models/text_encoders
[INFO] Adding extra search path upscale_models /Users/jaxon/ComfyUI-Shared/models/upscale_models
[INFO] Adding extra search path background_removal /Users/jaxon/ComfyUI-Shared/models/background_removal
[INFO] Adding extra search path frame_interpolation /Users/jaxon/ComfyUI-Shared/models/frame_interpolation
[INFO] Adding extra search path geometry_estimation /Users/jaxon/ComfyUI-Shared/models/geometry_estimation
[INFO] Adding extra search path optical_flow /Users/jaxon/ComfyUI-Shared/models/optical_flow
[INFO] Adding extra search path detection /Users/jaxon/ComfyUI-Shared/models/detection
[INFO] Adding extra search path vae /Users/jaxon/ComfyUI-Shared/models/vae
[INFO] Adding extra search path vae_approx /Users/jaxon/ComfyUI-Shared/models/vae_approx
[INFO] Adding extra search path clip /Users/jaxon/ComfyUI-Shared/models/clip
[INFO] Adding extra search path unet /Users/jaxon/ComfyUI-Shared/models/unet
[INFO] Setting output directory to: /Users/jaxon/ComfyUI-Shared/output
[INFO] Setting input directory to: /Users/jaxon/ComfyUI-Shared/input
[START] Security scan
[INFO] [ComfyUI-Manager] Using uv as Python module for pip operations.
[DONE] Security scan
** ComfyUI startup time: 2026-08-30 00:07:39.090
** Platform: Darwin
** Python version: 3.13.12 (main, Feb 12 2026, 01:06:02) [Clang 21.1.4 ]
** Python executable: /Users/jaxon/ComfyUI-Installs/ComfyUI/ComfyUI/.venv/bin/python3
** ComfyUI Path: /Users/jaxon/ComfyUI-Installs/ComfyUI/ComfyUI
** ComfyUI Base Folder Path: /Users/jaxon/ComfyUI-Installs/ComfyUI/ComfyUI
** User directory: /Users/jaxon/ComfyUI-Installs/ComfyUI/ComfyUI/user
** ComfyUI-Manager config path: /Users/jaxon/ComfyUI-Installs/ComfyUI/ComfyUI/user/__manager/config.ini
** Log path: /Users/jaxon/ComfyUI-Installs/ComfyUI/ComfyUI/user/comfyui.log
[INFO] [PRE] ComfyUI-Manager
[INFO] Found comfy_kitchen backend hip: {'available': False, 'disabled': False, 'unavailable_reason': 'PyTorch ROCm/HIP runtime not available', 'capabilities': []}
[INFO] Found comfy_kitchen backend eager: {'available': True, 'disabled': False, 'unavailable_reason': None, 'capabilities': ['adaln', 'apply_rope', 'apply_rope1', 'apply_rope1_', 'apply_rope_', 'apply_rope_split_half', 'apply_rope_split_half1', 'apply_rope_split_half1_', 'apply_rope_split_half_', 'convrot_w4a4_linear', 'dequantize_convrot_w4a4_weight', 'dequantize_int8_convrot_weight', 'dequantize_int8_convrot_weight_dtype', 'dequantize_int8_embedding', 'dequantize_int8_simple', 'dequantize_int8_simple_dtype', 'dequantize_mxfp8', 'dequantize_nvfp4', 'dequantize_per_tensor_fp8', 'dequantize_w4a8_int8_weight', 'gemv_awq_w4a16', 'int8_linear', 'na3d', 'prepare_int4_weight_for_int8_linear', 'quantize_and_rotate_rowwise', 'quantize_convrot_w4a4_weight', 'quantize_int8_convrot_weight', 'quantize_int8_rowwise', 'quantize_int8_tensorwise', 'quantize_mxfp8', 'quantize_nvfp4', 'quantize_per_tensor_fp8', 'quantize_svdquant_w4a4', 'quantize_w4a8_int8_weight', 'rms_adaln', 'rms_rope', 'rms_rope1', 'rms_rope1_', 'rms_rope_', 'rms_rope_split_half', 'rms_rope_split_half1', 'rms_rope_split_half1_', 'rms_rope_split_half_', 'rotate_int8_convrot_weight', 'scaled_mm_mxfp8', 'scaled_mm_nvfp4', 'scaled_mm_svdquant_w4a4', 'stochastic_rounding_fp8', 'w4a8_int8_linear']}
[INFO] Found comfy_kitchen backend triton: {'available': False, 'disabled': True, 'unavailable_reason': "ImportError: No module named 'triton'", 'capabilities': []}
[INFO] Found comfy_kitchen backend cuda: {'available': False, 'disabled': True, 'unavailable_reason': 'Extension file not found: /Users/jaxon/ComfyUI-Installs/ComfyUI/ComfyUI/.venv/lib/python3.13/site-packages/comfy_kitchen/backends/cuda/_C.abi3.so', 'capabilities': []}
[INFO] Checkpoint files will always be loaded safely.
[INFO] Total VRAM 131072 MB, total RAM 131072 MB
[INFO] pytorch version: 2.12.1
[INFO] Mac Version (26, 6)
[INFO] Set vram state to: SHARED
[INFO] Device: mps
[INFO] Using sub quadratic optimization for attention, if you have memory or speed issues try using: --use-split-cross-attention
[INFO] Python version: 3.13.12 (main, Feb 12 2026, 01:06:02) [Clang 21.1.4 ]
[INFO] ComfyUI version: 0.34.2
[INFO] comfy-aimdo version: 0.4.15
[INFO] comfy-kitchen version: 0.2.31
[INFO] comfyui-frontend-package version: 1.49.6
[INFO] comfyui-workflow-templates version: 0.11.50
[INFO] comfyui-embedded-docs version: 0.5.10
[INFO] comfy-kitchen version: 0.2.31
[INFO] comfy-aimdo version: 0.4.15
[INFO] [Prompt Server] web root: /Users/jaxon/ComfyUI-Installs/ComfyUI/ComfyUI/.venv/lib/python3.13/site-packages/comfyui_frontend_package/static
[INFO] Asset seeder disabled
[INFO] [START] ComfyUI-Manager
[ComfyUI-Manager] Using GitPython backend
[INFO] [ComfyUI-Manager] network_mode: public
[WARNING] [ComfyUI-Manager] The matrix sharing feature has been disabled because the `matrix-nio` dependency is not installed.
To use this feature, please run the following command:
/Users/jaxon/ComfyUI-Installs/ComfyUI/ComfyUI/.venv/bin/python3 -m pip install matrix-nio

[INFO] No OpenGL_accelerate module loaded: No module named 'OpenGL_accelerate'
[INFO]
Import times for custom nodes:
[INFO] 0.0 seconds: /Users/jaxon/ComfyUI-Installs/ComfyUI/ComfyUI/custom_nodes/websocket_image_save.py
[INFO]
[INFO] Context impl SQLiteImpl.
[INFO] Will assume non-transactional DDL.
[INFO] Using RAM pressure cache.
[INFO] Starting server

[INFO] To see the GUI go to: http://127.0.0.1:8188
[INFO] got prompt
[INFO] VAE load device: mps, offload device: cpu, dtype: torch.float32
[INFO] VAE load device: mps, offload device: cpu, dtype: torch.float16
[INFO] Found quantization metadata version 1
[INFO] Using MixedPrecisionOps for text encoder
[INFO] Requested to load MiniMaxH3TEModel_
[INFO] loaded completely; 14960.20 MB loaded, full load: True
[INFO] CLIP/text encoder model load device: cpu, offload device: cpu, current: cpu, dtype: torch.float16
[INFO] Found quantization metadata version 1
[INFO] Detected mixed precision quantization
[INFO] Using mixed precision operations
[INFO] Native ops: int8_tensorwise, asym_w4a8_int8, convrot_w4a4 , emulated ops: float8_e5m2, mxfp8, float8_e4m3fn, nvfp4
[INFO] model weight dtype torch.bfloat16, manual cast: torch.bfloat16
[INFO] model_type FLOW_AV
[INFO] Requested to load MiniMaxH3
[INFO] loaded completely; 19996.14 MB loaded, full load: True
0%| | 0/20 [00:00

Start with the attached video_minimax_h3_t2v.json workflow and reproduce it on the logged ComfyUI 0.34.2/PyTorch 2.12.1 MPS setup. Read the model-loading and MPS fallback messages around MiniMaxH3 and the 0% progress point. Done means explaining why execution remains at 0% on this Mac and documenting a verified way to run the official example or confirming the limitation.

Written by the indexing model from the issue text.