diff --git a/examples/autoround/README.md b/examples/autoround/README.md
index 3abdd7d17..b5f1ed738 100644
--- a/examples/autoround/README.md
+++ b/examples/autoround/README.md
@@ -91,7 +91,6 @@ oneshot(
     shuffle_calibration_samples=False,
 )
 
-
 # Save to disk compressed.
 SAVE_DIR = MODEL_ID.rstrip("/").split("/")[-1] + "-W4A16-G128-AutoRound"
 model.save_pretrained(SAVE_DIR, save_compressed=True)
@@ -125,6 +124,7 @@ lm_eval --model vllm \
 
 We can see the resulting scores look good!
 
+```text
 ```bash
 | Tasks | Version | Filter           | n-shot | Metric      |     | Value |     | Stderr |
 | ----- | ------: | ---------------- | -----: | ----------- | --- | ----: | --- | -----: |
diff --git a/examples/autoround/llama3_example.py b/examples/autoround/llama3_example.py
index 9843073bd..d2a2f3bec 100644
--- a/examples/autoround/llama3_example.py
+++ b/examples/autoround/llama3_example.py
@@ -2,9 +2,9 @@
 from transformers import AutoModelForCausalLM, AutoTokenizer
 
 from llmcompressor import oneshot
-from llmcompressor.modifiers.autoround import AutoRoundModifier
 from llmcompressor.utils import dispatch_for_generation
 
+
 # Select model and load it.
 model_id = "meta-llama/Meta-Llama-3-8B-Instruct"
 model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype="auto")
@@ -21,14 +21,12 @@
     nsamples=NUM_CALIBRATION_SAMPLES,
 )
 
-
 # Configure the quantization algorithm to run.
 #   * quantize the weights to 4 bit with AutoRound with a group size 128
 recipe = AutoRoundModifier(
     targets="Linear", scheme="W4A16", ignore=["lm_head"], iters=200
 )
 
-
 # Apply algorithms.
 oneshot(
     model=model,
diff --git a/examples/autoround/quantization_kv_cache/llama3_example.py b/examples/autoround/quantization_kv_cache/llama3_example.py
new file mode 100644
index 000000000..b47b3df61
--- /dev/null
+++ b/examples/autoround/quantization_kv_cache/llama3_example.py
@@ -0,0 +1,68 @@
+from auto_round.calib_dataset import get_dataset
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+from llmcompressor import oneshot
+from llmcompressor.utils import dispatch_for_generation
+
+
+# Select model and load it.
+model_id = "meta-llama/Meta-Llama-3-8B-Instruct"
+model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype="auto")
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+
+# Select calibration dataset.
+NUM_CALIBRATION_SAMPLES = 128
+MAX_SEQUENCE_LENGTH = 2048
+# Get aligned calibration dataset.
+
+ds = get_dataset(
+    tokenizer=tokenizer,
+    seqlen=MAX_SEQUENCE_LENGTH,
+    nsamples=NUM_CALIBRATION_SAMPLES,
+)
+
+# Configure the quantization algorithm to run.
+#   * quantize the weights to 4 bit with AutoRound with a group size 128
+#   * quantize the kv cache to fp8
+recipe = """
+quant_stage:
+  quant_modifiers:
+    QuantizationModifier:
+      kv_cache_scheme:
+        num_bits: 8
+        type: float
+        strategy: tensor
+        dynamic: false
+        symmetric: true
+    AutoRoundModifier:
+      targets: [Linear]
+      scheme: W4A16
+      ignore: [lm_head]
+      iters: 200
+"""
+
+# Apply algorithms.
+oneshot(
+    model=model,
+    dataset=ds,
+    recipe=recipe,
+    max_seq_length=MAX_SEQUENCE_LENGTH,
+    num_calibration_samples=NUM_CALIBRATION_SAMPLES,
+    # disable shuffling to get slightly better mmlu score
+    shuffle_calibration_samples=False,
+)
+
+# Confirm generations of the quantized model look sane.
+print("\n\n")
+print("========== SAMPLE GENERATION ==============")
+dispatch_for_generation(model)
+sample = tokenizer("Hello my name is", return_tensors="pt")
+sample = {key: value.to(model.device) for key, value in sample.items()}
+output = model.generate(**sample, max_new_tokens=100)
+print(tokenizer.decode(output[0]))
+print("==========================================\n\n")
+
+# Save to disk compressed.
+SAVE_DIR = model_id.rstrip("/").split("/")[-1] + "-W4A16-G128-AutoRound"
+model.save_pretrained(SAVE_DIR, save_compressed=True)
+tokenizer.save_pretrained(SAVE_DIR)