SAM 3.1 Multiplex (HSWQ ConvRot INT8)

High-fidelity HSWQ ConvRot INT8 (Hybrid-Sensitivity-Weighted-Quantization) quantized weights for the SAM 3.1 Multiplex (Segment Anything Model 3.1) architecture.

πŸ“¦ Model Details

Filename Base Architecture Precision / Format File Size Size Reduction vs FP16 Native ComfyUI Support Status
sam3.1_multiplex_hswq_convrot_int8.safetensors SAM 3.1 Multiplex HSWQ ConvRot INT8 (int8_tensorwise) ~1,738.2 MB (1.74 GB) ~0.4% Reduction vs the ~1,745.5 MB (1.75 GB) FP16 source - 41 of the 221 runtime-live Linear layers are quantised, the rest of the checkpoint stays FP16 βœ… Supported natively (UNetLoader) Available

Sizes are decimal MB/GB computed from the published byte counts, and the reduction is computed from those same byte counts against the source file named in the same row.

πŸš€ Usage in ComfyUI

Model Placement

Download sam3.1_multiplex_hswq_convrot_int8.safetensors and place it in your ComfyUI models directory:

ComfyUI/models/unet/sam3.1_multiplex_hswq_convrot_int8.safetensors

Loading

  1. Load the model using the standard UNetLoader (or Load Diffusion Model) node in ComfyUI, or use HSWQ SAM3 Loader from ComfyUI-HSWQ-Loader-and-Tools.
  2. Connect the loaded model output directly into your SAM3 image / video segmentation workflow nodes.
  3. ComfyUI automatically detects the comfy_quant header metadata and executes optimized INT8 Tensor Core operations natively.

πŸ”’ Security

Backdoor audit. Each file's audit status - verdict strength, weight coverage, the record behind it, and the limits of what that measurement can show - is in Backdoor Audit Verdicts. The audit code, the procedure and the raw records are in the same repository.

πŸ“œ Credits & License

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. πŸ™‹ Ask for provider support

Model tree for ussoewwin/SAM3.1-HSWQ-ConvRot-INT8

Base model

facebook/sam3.1
Finetuned
Comfy-Org/sam3.1
Finetuned
(1)
this model