diff --git a/README.md b/README.md
index e5cfeb9..1d19a69 100644
--- a/README.md
+++ b/README.md
@@ -1,6 +1,6 @@
 # Print unsigned 16-bit
 
-6502 assembly code to print an unsigned 16-bit in 95 bytes ($5F).
+6502 assembly code to print an unsigned 16-bit in 91 bytes ($5B).
 
 Features:
 
@@ -14,18 +14,18 @@ Copy/Paste into your favorite emulator.
 
 ```asm
 0800:A9 12 A2 34 4C 07 08 8E
-0808:64 08 8D 65 08 A9 00 8D
-0810:60 08 8D 61 08 8D 62 08
-0818:A2 10 F8 0E 64 08 2E 65
-0820:08 A0 FD B9 63 07 79 63
-0828:07 99 63 07 C8 D0 F4 CA
-0830:D0 E9 D8 A0 03 B9 5F 08
-0838:20 44 08 88 D0 F7 8A E0
-0840:00 F0 11 60 48 20 7B F8
-0848:20 4E 08 68 29 0F D0 04
-0850:E0 00 F0 EF C9 0A 90 02
-0858:69 06 69 B0 E8 4C ED FD
-0860:00 00 00 00 00 00 
+0808:61 08 48 A2 00 8E 5D 08
+0810:8E 5E 08 8E 5F 08 A2 10
+0818:F8 0E 61 08 68 2A 48 A0
+0820:FD B9 60 07 79 60 07 99
+0828:60 07 C8 D0 F4 CA D0 E9
+0830:68 D8 A0 03 B9 5C 08 20
+0838:41 08 88 D0 F7 8A F0 11
+0840:60 48 20 7B F8 20 4B 08
+0848:68 29 0F D0 04 E0 00 F0
+0850:EF C9 0A 90 02 69 06 69
+0858:B0 E8 4C ED FD 00 00 00
+0860:00 00
 ```
 
 
diff --git a/print_uint16 b/print_uint16
index a05da9f..8bdc163 100644
Binary files a/print_uint16 and b/print_uint16 differ
diff --git a/print_uint16.s b/print_uint16.s
index 7fc7af0..9be865b 100644
--- a/print_uint16.s
+++ b/print_uint16.s
@@ -17,20 +17,24 @@ SCRN2   = $F879
 ; Also see: Applesoft LINPRT @ ED24
 ; ======================================================================
 PrintUint16
-        STX _temp+0
-        STA _temp+1
+        STX _temp  
+        PHA             ; Optimized: STA _temp+1
 
-        LDA #0
-        STA _bcd+0
-        STA _bcd+1
-        STA _bcd+2
+        LDX #0
+        STX _bcd+0
+        STX _bcd+1
+        STX _bcd+2
 
 Dec2BCD
         LDX   #16       ; 16 bits
         SED             ; "Double Dabble"
 _Dec2BCD                ; https://en.wikipedia.org/wiki/Double_dabble
-        ASL _temp+0
-        ROL _temp+1
+        ASL _temp+0     ;     abcd efgh | ijkl mnop |
+;       ROL _temp+1     ; C=a bcde fghi | jklm nop0 |
+;                       ; Bit 7654_3210 | 7654_3210 |
+        PLA
+        ROL
+        PHA
 
         LDY #$FD        ; $00-$FD=-3 bcd[0] bcd[1] bcd[2] bcd[3]
 _DoubleDabble           ;              Y=FD   Y=FE   Y=FF   Y=00
@@ -39,9 +43,10 @@ _DoubleDabble           ;              Y=FD   Y=FE   Y=FF   Y=00
         STA _bcd-$FD,Y
         INY
         BNE _DoubleDabble
-
         DEX
         BNE _Dec2BCD
+
+        PLA             ; keep stack
         CLD             ; X=0 = output length
 
 DecWidth
@@ -52,8 +57,7 @@ BCD2Chars
         DEY
         BNE BCD2Chars
 
-        TXA
-        CPX #0          ; Handle special case input = $0000 of no output
+        TXA             ; Handle special case input = $0000 of no output
         BEQ  _HaveLeadingDigit
 
 _PrintDone
@@ -84,5 +88,5 @@ PutChar
         JMP COUT
 
 _bcd    ds  4   ; 6 chars for printing dec
-_temp   db  0,0
+_temp   db  0