diff --git a/README.md b/README.md
index 67ac5df..0685cc6 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 124 bytes ($7C).
+6502 assembly code to print an unsigned 16-bit in 117 bytes ($75).
 
 
 * No zero-page usage
@@ -13,22 +13,21 @@ Copy/Paste into your favorite emulator.
 
 ```asm
 0800:A9 12 A2 34 4C 07 08 8E
-0808:81 08 8D 82 08 A9 00 8D
-0810:6F 08 8D 77 08 8D 78 08
-0818:8D 79 08 A2 10 F8 0E 81
-0820:08 2E 82 08 A0 FD B9 7A
-0828:07 79 7A 07 99 7A 07 C8
-0830:D0 F4 CA D0 E9 D8 A0 03
-0838:B9 77 08 20 5B 08 88 10
-0840:F7 C8 CC 6F 08 F0 07 B9
-0848:7B 08 C9 B0 F0 F3 B9 7B
-0850:08 20 ED FD C8 CC 6F 08
-0858:90 F4 60 48 4A 4A 4A 4A
-0860:20 64 08 68 29 0F C9 0A
-0868:90 02 69 06 69 B0 A2 00
-0870:9D 7B 08 EE 6F 08 60 00
-0878:00 00 00 00 00 00 00 00
-0880:00 00 00 
+0808:7A 08 8D 7B 08 A9 00 8D
+0810:70 08 8D 71 08 8D 72 08
+0818:A2 10 F8 0E 7A 08 2E 7B
+0820:08 A0 FD B9 73 07 79 73
+0828:07 99 73 07 C8 D0 F4 CA
+0830:D0 E9 D8 A0 04 A9 B0 8D
+0838:74 08 B9 6F 08 20 53 08
+0840:88 D0 F7 8E 70 08 B9 74
+0848:08 20 ED FD C8 CC 70 08
+0850:90 F4 60 48 20 7B F8 20
+0858:5D 08 68 29 0F D0 04 E0
+0860:00 F0 0C C9 0A 90 02 69
+0868:06 69 B0 9D 74 08 E8 60
+0870:00 00 00 00 00 00 00 00
+0878:00 00 00 00 
 ```
 
 
diff --git a/print_uint16 b/print_uint16
index aa8fd5b..44bf318 100644
Binary files a/print_uint16 and b/print_uint16 differ
diff --git a/print_uint16.s b/print_uint16.s
index aaa1953..9b35179 100644
--- a/print_uint16.s
+++ b/print_uint16.s
@@ -1,3 +1,7 @@
+; Michael Pohoreski
+; Optimized from printm
+; Thanks to qkumba for optimizations
+; F8 ROM Entry Points
 COUT    = $FDED
 SCRN2   = $F879
 
@@ -41,23 +45,19 @@ _DoubleDabble           ;              Y=FD   Y=FE   Y=FF   Y=00
         CLD             ; X=0 = output length
 
 DecWidth
-        LDY #3          ; intentional buffer overflow - 8 digit output for special case of $0000
+        LDY #4          ; 6 digit output for special case of $0000
+
+        LDA #'0' + $80  ; handle special case input = $0000
+        STA _output     ; since we always print at least 1 digit
+
 BCD2Chars
-        LDA _bcd,Y
+        LDA _bcd-1,Y
         JSR HexA        ; _output[0..7] = '?'
         DEY
-        BPL BCD2Chars
+        BNE BCD2Chars
 
         STX _len        ; output buffer len = num digits to print
 
-SkipLeadZero
-        INY
-        CPY _len
-        BEQ OutDigits
-        LDA _output,Y
-        CMP #'0' + $80  ; skip all leading zero's
-        BEQ SkipLeadZero
-
 OutDigits
         LDA _output,Y   ; always print digit in "ones" place
         JSR COUT
@@ -77,7 +77,13 @@ HexA
         PLA
         AND #$F
 _HexNib
+        BNE _HaveLeadingDigit   ; If have leading zero and no output yet ...
+        CPX #0                  ; ... then skip storing it
+        BEQ _HexAsciiDone
+
+_HaveLeadingDigit
         CMP #$A         ; n < 10 ?
+
         BCC _Hex2Asc
         ADC #6          ; n += 6    $A -> +6 + (C=1) = $11
 _Hex2Asc
@@ -85,6 +91,7 @@ _Hex2Asc
 PutChar
         STA _output,X
         INX             ; X = output string length
+_HexAsciiDone
         RTS