diff --git a/benchmarks/mem/quicksort.bril b/benchmarks/mem/quicksort.bril
new file mode 100644
index 000000000..b7e0f7f15
--- /dev/null
+++ b/benchmarks/mem/quicksort.bril
@@ -0,0 +1,125 @@
+# An implementation of Quicksort using the Lomuto partition scheme, adapted from the pseudocode on Wikipedia
+# Input: an array of length 6
+# Output: the input array sorted in ascending order
+# Adopted two helper functions, pack and print_array, from Jiajie Li's bubble sort benchmark
+
+# ARGS: 94 21 5 6 82 46
+@main(n1: int, n2: int, n3: int, n4: int, n5: int, n6:int) {
+    size: int = const 6;
+    array: ptr<int> = call @pack size n1 n2 n3 n4 n5 n6;
+    one: int = const 1;
+    size_minus_one: int = sub size one;
+
+    zero: int = const 0;
+    call @qsort array zero size_minus_one;
+
+    # Print array
+    call @print_array array size;
+
+    free array;
+}
+
+@qsort(array : ptr<int>, l: int, r:int) {
+    # if l >= r or r < 0, return
+    l_ge_r: bool = ge l r;
+    zero: int = const 0;
+    neg_r: bool = lt r zero;
+    ret_cond: bool = or l_ge_r neg_r;
+
+    br ret_cond .done .continue; 
+
+    .continue:
+        p: int = call @partition array l r;
+        one: int = const 1;
+        p_minus_one: int = sub p one;
+        p_plus_one: int = add p one;
+
+        call @qsort array l p_minus_one;
+        call @qsort array p_plus_one r;
+
+    .done:
+        ret;
+}
+
+@partition(array : ptr<int>, l: int, r:int) : int {
+    # choose the last element as the pivot
+    pivot_loc: ptr<int> = ptradd array r;
+    pivot: int = load pivot_loc;
+    one: int = const 1;
+    i:int = sub l one;
+    j:int = id i;
+
+    .loop.init:
+        j:int = add j one;
+        cond: bool = lt j r;
+        br cond .body .post.loop;
+
+    .body:
+        j_loc: ptr<int> = ptradd array j;
+        a_j: int = load j_loc;
+        swap_cond: bool = le a_j pivot;
+        br swap_cond .swap .loop.init;
+
+    .swap:
+        # increment i by 1
+        i: int = add i one;
+
+        # swap the current element with the element at the temporary pivot index i
+        i_loc: ptr<int> = ptradd array i;
+        a_i: int = load i_loc;
+        store j_loc a_i;
+        store i_loc a_j;
+        jmp .loop.init;
+
+    .post.loop:
+        i:int = add i one;
+        i_loc: ptr<int> = ptradd array i;
+        a_i: int = load i_loc;
+        store i_loc pivot;
+        store pivot_loc a_i;
+        ret i;
+}
+
+# allocate an array of the given size and pack the input values into the array
+@pack(size: int, n1: int, n2: int, n3: int, n4: int, n5: int, n6: int) : ptr<int> {
+    one: int = const 1;
+    i: int = const 0;
+    array: ptr<int> = alloc size;
+# Pack data into array manually. Cannot use loop because of the different var name.     
+    loc: ptr<int> = ptradd array i;
+    store loc n1;
+    i: int = add i one;
+    loc: ptr<int> = ptradd array i;
+    store loc n2;
+    i: int = add i one;        
+    loc: ptr<int> = ptradd array i;
+    store loc n3;
+    i: int = add i one;        
+    loc: ptr<int> = ptradd array i;
+    store loc n4;
+    i: int = add i one;        
+    loc: ptr<int> = ptradd array i;
+    store loc n5;
+    i: int = add i one;        
+    loc: ptr<int> = ptradd array i;
+    store loc n6;
+
+    ret array;
+}
+
+@print_array(array: ptr<int>, size: int) {
+    i: int = const 0;
+    one: int = const 1;
+.loop:
+    cond: bool = lt i size;
+    br cond .body .done;
+.body:
+    loc: ptr<int> = ptradd array i;
+    val: int = load loc;
+    print val;
+.loop_end:
+    i: int = add i one;
+    jmp .loop;
+.done:
+    ret;
+}
\ No newline at end of file
diff --git a/benchmarks/mem/quicksort.out b/benchmarks/mem/quicksort.out
new file mode 100644
index 000000000..0ab8cac08
--- /dev/null
+++ b/benchmarks/mem/quicksort.out
@@ -0,0 +1,6 @@
+5
+6
+21
+46
+82
+94
diff --git a/benchmarks/mem/quicksort.prof b/benchmarks/mem/quicksort.prof
new file mode 100644
index 000000000..32b1ccbf7
--- /dev/null
+++ b/benchmarks/mem/quicksort.prof
@@ -0,0 +1 @@
+total_dyn_inst: 264
diff --git a/docs/tools/bench.md b/docs/tools/bench.md
index 2cb2625c6..0f72c85f5 100644
--- a/docs/tools/bench.md
+++ b/docs/tools/bench.md
@@ -49,6 +49,7 @@ The current benchmarks are:
 * `primitive-root`: Computes a [primitive root][primitive_root] modulo a prime number input.
 * `pythagorean_triple`: Prints all Pythagorean triples with the given c, if such triples exist. An intentionally very naive implementation.
 * `quadratic`: The [quadratic formula][qf], including a hand-rolled implementation of square root.
+* `quicksort`: [Quicksort using the Lomuto partition scheme][qsort]. 
 * `recfact`: Compute *n!* using recursive function calls.
 * `rectangles-area-difference`: Output the difference between the areas of rectangles (as a positive value) given their respective side lengths.
 * `relative-primes`: Print all numbers relatively prime to *n* using [Euclidean algorithm][euclidean_into].
@@ -92,5 +93,6 @@ Credit for several of these benchmarks goes to Alexa VanHattum and Gregory Yaune
 [palindrome]: https://en.wikipedia.org/wiki/Palindrome
 [hanoi]: https://en.wikipedia.org/wiki/Tower_of_Hanoi
 [euler]: https://en.wikipedia.org/wiki/E_(mathematical_constant)
+[qsort]: https://en.wikipedia.org/wiki/Quicksort#Lomuto_partition_scheme
 [modinv]: https://en.wikipedia.org/wiki/Modular_multiplicative_inverse
 [totient]: https://en.wikipedia.org/wiki/Euler's_totient_function