Model tools
Understand a supported model file before using it. Inspect containers and tensor descriptors without executing model code or unpickling checkpoints.
Have a file already? Start in the workspace →Model viewers
Read supported Safetensors, ONNX, GGUF, NumPy and PyTorch container metadata. Inspection is bounded and is not model inference.
Read Safetensors, ONNX, GGUF, NumPy and PyTorch containers.
SAFETENSORS · ONNX · GGUF · NPY · NPZ · PT · PTH · CKPTCount model parametersCount tensor elements and list per-tensor sizes from supported model descriptors without loading a machine-learning framework.
SAFETENSORS · ONNX · GGUFEstimate model memoryEstimate weight storage at common precisions from tensor shapes. Compare FP32, FP16 and INT8 weight footprints before choosing a device.
SAFETENSORS · ONNX · GGUFView an ONNX graphView ONNX operators and their tensor connections as a graph. Inspect input and output descriptors without running inference.
ONNXTensor operations
Extract a named Safetensors tensor or inspect supported floating-point values for statistics, NaN and infinity.
Save a Safetensors tensor as NumPy or Safetensors.
SAFETENSORSCheck tensor valuesFind NaN, infinity and statistics in F32/F64 tensors.
SAFETENSORSPlot a tensor histogramRead one F32 or F64 Safetensors tensor and group finite values into histogram bins. Count NaN and infinity separately.
SAFETENSORSSplit or merge SafetensorsSplit a Safetensors file at tensor boundaries or combine shards into one file. A split ZIP includes an index mapping tensor names to shards.
SAFETENSORSModel comparison
Compare names, shapes and data types in two supported model descriptor sets. Matching descriptors do not imply equal model weights.