docs: add Size column to Performance table

README.md

@@ -113,11 +113,11 @@ seg_map = logits.argmax(axis=1).squeeze()  # (H, W)
 
 Benchmarked on CPU (16-core, 8 ORT threads, `intra_op_num_threads=8`):
 
-| Backend | Latency | Speedup |
-|---------|---------|---------|
-| PyTorch FP32 | ~430 ms | 1× |
-| ONNX FP32 | ~293 ms | 1.5× |
-| ONNX INT8 static | ~229 ms | **1.9×** |
+| Backend | Latency | Speedup | Size |
+|---------|---------|---------|------|
+| PyTorch FP32 | ~430 ms | 1× | 256 MB |
+| ONNX FP32 | ~293 ms | 1.5× | 257 MB |
+| ONNX INT8 static | ~229 ms | **1.9×** | **66 MB** |
 
 INT8 static quantization achieves **99.94% pixel-level agreement** with the FP32 model.