Local validation report — H3 FL2VA on Apple Silicon
Status
Blocked for a functional local generation through the official quantized ComfyUI path. Installation and model loading succeed; sampling fails on the first iteration because an MPS operator is unavailable.
Machine
Mac Studio Mac14,14 — Apple M2 Ultra, 24 CPU, 60 GPU, 64 GB unified memory, Metal 4, macOS 26.5.2.
Tested backend
ComfyUI stock 0.33.0 + PyTorch 2.13.0 + MPS, with no additional H3 custom node and no Sage Attention. Outside the sandbox, mps_available=True and ComfyUI detects Device: mps.
Models
minimax_h3_fl2va_pruned_int8_convrot.safetensors — ~20 GiBqwen3vl_32b_minimax_h3_nvfp4_awq.safetensors — ~15 GiB- Video VAE — ~4.8 GiB
- Audio VAE — ~577 MiB
The FL2VA download total was confirmed at 42.5 GiB before transfer. Ref2VA and BF16/full variants were not downloaded.
First test
Native local T2VA workflow, audio enabled, 124 frames at 24 fps (~5 seconds), 608x352 preview, 20 steps, fixed seed and simple prompt.
The prompt was accepted locally (node_errors: {}). The text encoder loaded 14,960 MB and the DiT loaded 19,996 MB. Sampling failed after 47.92 seconds at 0/20 steps. No MP4 was produced.
Error
NotImplementedError: The operator 'aten::_int_mm' is not currently implemented for the MPS device
The error occurs in the INT8 quantized comfy_kitchen path used by the DiT ConvRot implementation. PyTorch suggests PYTORCH_ENABLE_MPS_FALLBACK=1, but that would move the operation to CPU and would not constitute a satisfactory native MPS baseline.
Memory compression and swap were also non-zero after the failed run.
Recommendation
Please clarify whether Apple Silicon/MPS is expected to support the official INT8/NVFP4/AWQ ComfyUI workflow. A Diffusers/MPS route or an explicit BF16/CPU route may be worth testing separately. Until aten::_int_mm is implemented for MPS, the current quantized ComfyUI path should not be treated as a working Apple Silicon baseline.
Local validation report — H3 FL2VA on Apple Silicon
Status
Blocked for a functional local generation through the official quantized ComfyUI path. Installation and model loading succeed; sampling fails on the first iteration because an MPS operator is unavailable.
Machine
Mac Studio Mac14,14 — Apple M2 Ultra, 24 CPU, 60 GPU, 64 GB unified memory, Metal 4, macOS 26.5.2.
Tested backend
ComfyUI stock 0.33.0 + PyTorch 2.13.0 + MPS, with no additional H3 custom node and no Sage Attention. Outside the sandbox,
mps_available=Trueand ComfyUI detectsDevice: mps.Models
minimax_h3_fl2va_pruned_int8_convrot.safetensors— ~20 GiBqwen3vl_32b_minimax_h3_nvfp4_awq.safetensors— ~15 GiBThe FL2VA download total was confirmed at 42.5 GiB before transfer. Ref2VA and BF16/full variants were not downloaded.
First test
Native local T2VA workflow, audio enabled, 124 frames at 24 fps (~5 seconds), 608x352 preview, 20 steps, fixed seed and simple prompt.
The prompt was accepted locally (
node_errors: {}). The text encoder loaded 14,960 MB and the DiT loaded 19,996 MB. Sampling failed after 47.92 seconds at 0/20 steps. No MP4 was produced.Error
The error occurs in the INT8 quantized
comfy_kitchenpath used by the DiT ConvRot implementation. PyTorch suggestsPYTORCH_ENABLE_MPS_FALLBACK=1, but that would move the operation to CPU and would not constitute a satisfactory native MPS baseline.Memory compression and swap were also non-zero after the failed run.
Recommendation
Please clarify whether Apple Silicon/MPS is expected to support the official INT8/NVFP4/AWQ ComfyUI workflow. A Diffusers/MPS route or an explicit BF16/CPU route may be worth testing separately. Until
aten::_int_mmis implemented for MPS, the current quantized ComfyUI path should not be treated as a working Apple Silicon baseline.