diff --git a/lib/trino-parquet/src/main/java/io/trino/parquet/ParquetReaderUtils.java b/lib/trino-parquet/src/main/java/io/trino/parquet/ParquetReaderUtils.java
index a608955e9b8d..77ae5bcf40ab 100644
--- a/lib/trino-parquet/src/main/java/io/trino/parquet/ParquetReaderUtils.java
+++ b/lib/trino-parquet/src/main/java/io/trino/parquet/ParquetReaderUtils.java
@@ -52,35 +52,35 @@ public static int readUleb128Int(SimpleSliceInputStream input)
     {
         byte[] inputBytes = input.getByteArray();
         int offset = input.getByteArrayOffset();
-        // Manual loop unrolling shows improvements in BenchmarkReadUleb128Int
-        int inputByte = inputBytes[offset];
-        int value = inputByte & 0x7F;
-        if ((inputByte & 0x80) == 0) {
+        // Fast paths for 1-byte and 2-byte values (most common for small dictionary indices
+        // and page/group counts). For 3+ byte values, fall through to a tight loop. This beats
+        // the fully unrolled 5-branch version on long input sequences (where the unrolled
+        // version's branch chain depth dominates), while preserving straight-line code for
+        // the common short values (where the unrolled version wins).
+        byte b0 = inputBytes[offset];
+        if ((b0 & 0x80) == 0) {
             input.skip(1);
-            return value;
+            return b0;
         }
-        inputByte = inputBytes[offset + 1];
-        value |= (inputByte & 0x7F) << 7;
-        if ((inputByte & 0x80) == 0) {
+        byte b1 = inputBytes[offset + 1];
+        int value = (b0 & 0x7F) | ((b1 & 0x7F) << 7);
+        if ((b1 & 0x80) == 0) {
             input.skip(2);
             return value;
         }
-        inputByte = inputBytes[offset + 2];
-        value |= (inputByte & 0x7F) << 14;
-        if ((inputByte & 0x80) == 0) {
-            input.skip(3);
-            return value;
-        }
-        inputByte = inputBytes[offset + 3];
-        value |= (inputByte & 0x7F) << 21;
-        if ((inputByte & 0x80) == 0) {
-            input.skip(4);
-            return value;
+        int consumed = 2;
+        int shift = 14;
+        byte b;
+        do {
+            b = inputBytes[offset + consumed];
+            value |= (b & 0x7F) << shift;
+            shift += 7;
+            consumed++;
         }
-        inputByte = inputBytes[offset + 4];
-        verify((inputByte & 0x80) == 0, "ULEB128 variable-width integer should not be longer than 5 bytes");
-        input.skip(5);
-        return value | inputByte << 28;
+        while ((b & 0x80) != 0 && shift < 35);
+        verify((b & 0x80) == 0, "ULEB128 variable-width integer should not be longer than 5 bytes");
+        input.skip(consumed);
+        return value;
     }
 
     public static long readUleb128Long(SimpleSliceInputStream input)