Oh dang...you're right

    $ csc -optimize-level 5 fib.scm 
    $ time ./fib

    real 0m5.506s
    user 0m5.489s
    sys  0m0.010s

I could get a few fractions of a second better playing with the stack size (4 MB was the best, 8 MB or above would segfault)

    $ csc -optimize-level 5 -stack-size 4m fib.scm 
    $ time ./fib

    real 0m5.295s
    user 0m5.277s
    sys  0m0.011s

Everything else was negligible or extremely varied.

Yep, to get beyond that you basically have to stop writing scheme and start writing a tortured variant of Chicken, for performance. ;)

I stopped writing Chicken scheme code a few years ago; it was fun due to the ease of interoperating with C, but I found Chibi a better fit for that niche eventually.