diff --git a/integration-tests/models/__snapshots__/test_flash_mixtral_awq/test_flash_mixtral_awq.json b/integration-tests/models/__snapshots__/test_flash_mixtral_awq/test_flash_mixtral_awq.json
new file mode 100644
index 00000000..9ca22e10
--- /dev/null
+++ b/integration-tests/models/__snapshots__/test_flash_mixtral_awq/test_flash_mixtral_awq.json
@@ -0,0 +1,104 @@
+{
+  "details": {
+    "best_of_sequences": null,
+    "finish_reason": "length",
+    "generated_tokens": 10,
+    "prefill": [
+      {
+        "id": 1,
+        "logprob": null,
+        "text": "<s>"
+      },
+      {
+        "id": 1824,
+        "logprob": -12.296875,
+        "text": "What"
+      },
+      {
+        "id": 349,
+        "logprob": -0.97216797,
+        "text": "is"
+      },
+      {
+        "id": 3534,
+        "logprob": -10.1796875,
+        "text": "deep"
+      },
+      {
+        "id": 5168,
+        "logprob": -0.9658203,
+        "text": "learning"
+      },
+      {
+        "id": 28804,
+        "logprob": -0.44384766,
+        "text": "?"
+      }
+    ],
+    "seed": null,
+    "tokens": [
+      {
+        "id": 13,
+        "logprob": -0.50878906,
+        "special": false,
+        "text": "\n"
+      },
+      {
+        "id": 13,
+        "logprob": -0.8876953,
+        "special": false,
+        "text": "\n"
+      },
+      {
+        "id": 23229,
+        "logprob": -0.15124512,
+        "special": false,
+        "text": "Deep"
+      },
+      {
+        "id": 5168,
+        "logprob": -0.030288696,
+        "special": false,
+        "text": " learning"
+      },
+      {
+        "id": 349,
+        "logprob": -0.16687012,
+        "special": false,
+        "text": " is"
+      },
+      {
+        "id": 264,
+        "logprob": -0.17858887,
+        "special": false,
+        "text": " a"
+      },
+      {
+        "id": 19804,
+        "logprob": -0.8046875,
+        "special": false,
+        "text": " subset"
+      },
+      {
+        "id": 302,
+        "logprob": -0.007205963,
+        "special": false,
+        "text": " of"
+      },
+      {
+        "id": 5599,
+        "logprob": -0.090026855,
+        "special": false,
+        "text": " machine"
+      },
+      {
+        "id": 5168,
+        "logprob": -0.0030670166,
+        "special": false,
+        "text": " learning"
+      }
+    ],
+    "top_tokens": null
+  },
+  "generated_text": "\n\nDeep learning is a subset of machine learning"
+}
diff --git a/integration-tests/models/__snapshots__/test_flash_mixtral_awq/test_flash_mixtral_awq_all_params.json b/integration-tests/models/__snapshots__/test_flash_mixtral_awq/test_flash_mixtral_awq_all_params.json
new file mode 100644
index 00000000..38ab7263
--- /dev/null
+++ b/integration-tests/models/__snapshots__/test_flash_mixtral_awq/test_flash_mixtral_awq_all_params.json
@@ -0,0 +1,99 @@
+{
+  "details": {
+    "best_of_sequences": null,
+    "finish_reason": "length",
+    "generated_tokens": 10,
+    "prefill": [
+      {
+        "id": 1,
+        "logprob": null,
+        "text": "<s>"
+      },
+      {
+        "id": 349,
+        "logprob": -13.921875,
+        "text": "is"
+      },
+      {
+        "id": 3534,
+        "logprob": -11.2265625,
+        "text": "deep"
+      },
+      {
+        "id": 5168,
+        "logprob": -2.3886719,
+        "text": "learning"
+      },
+      {
+        "id": 28804,
+        "logprob": -4.7109375,
+        "text": "?"
+      }
+    ],
+    "seed": 0,
+    "tokens": [
+      {
+        "id": 13,
+        "logprob": 0.0,
+        "special": false,
+        "text": "\n"
+      },
+      {
+        "id": 23229,
+        "logprob": -0.5229492,
+        "special": false,
+        "text": "Deep"
+      },
+      {
+        "id": 17504,
+        "logprob": 0.0,
+        "special": false,
+        "text": " Learning"
+      },
+      {
+        "id": 349,
+        "logprob": -0.5151367,
+        "special": false,
+        "text": " is"
+      },
+      {
+        "id": 264,
+        "logprob": 0.0,
+        "special": false,
+        "text": " a"
+      },
+      {
+        "id": 19804,
+        "logprob": 0.0,
+        "special": false,
+        "text": " subset"
+      },
+      {
+        "id": 302,
+        "logprob": 0.0,
+        "special": false,
+        "text": " of"
+      },
+      {
+        "id": 13253,
+        "logprob": -1.3359375,
+        "special": false,
+        "text": " Machine"
+      },
+      {
+        "id": 17504,
+        "logprob": 0.0,
+        "special": false,
+        "text": " Learning"
+      },
+      {
+        "id": 28725,
+        "logprob": 0.0,
+        "special": false,
+        "text": ","
+      }
+    ],
+    "top_tokens": null
+  },
+  "generated_text": "What is deep learning?\nDeep Learning is a subset of Machine Learning,"
+}
diff --git a/integration-tests/models/__snapshots__/test_flash_mixtral_awq/test_flash_mixtral_awq_load.json b/integration-tests/models/__snapshots__/test_flash_mixtral_awq/test_flash_mixtral_awq_load.json
new file mode 100644
index 00000000..329d73ee
--- /dev/null
+++ b/integration-tests/models/__snapshots__/test_flash_mixtral_awq/test_flash_mixtral_awq_load.json
@@ -0,0 +1,418 @@
+[
+  {
+    "details": {
+      "best_of_sequences": null,
+      "finish_reason": "length",
+      "generated_tokens": 10,
+      "prefill": [
+        {
+          "id": 1,
+          "logprob": null,
+          "text": "<s>"
+        },
+        {
+          "id": 1824,
+          "logprob": -12.296875,
+          "text": "What"
+        },
+        {
+          "id": 349,
+          "logprob": -0.97216797,
+          "text": "is"
+        },
+        {
+          "id": 3534,
+          "logprob": -10.1796875,
+          "text": "deep"
+        },
+        {
+          "id": 5168,
+          "logprob": -0.9658203,
+          "text": "learning"
+        },
+        {
+          "id": 28804,
+          "logprob": -0.44384766,
+          "text": "?"
+        }
+      ],
+      "seed": null,
+      "tokens": [
+        {
+          "id": 13,
+          "logprob": -0.50878906,
+          "special": false,
+          "text": "\n"
+        },
+        {
+          "id": 13,
+          "logprob": -0.8876953,
+          "special": false,
+          "text": "\n"
+        },
+        {
+          "id": 23229,
+          "logprob": -0.15136719,
+          "special": false,
+          "text": "Deep"
+        },
+        {
+          "id": 5168,
+          "logprob": -0.030273438,
+          "special": false,
+          "text": " learning"
+        },
+        {
+          "id": 349,
+          "logprob": -0.1665039,
+          "special": false,
+          "text": " is"
+        },
+        {
+          "id": 264,
+          "logprob": -0.1776123,
+          "special": false,
+          "text": " a"
+        },
+        {
+          "id": 19804,
+          "logprob": -0.8076172,
+          "special": false,
+          "text": " subset"
+        },
+        {
+          "id": 302,
+          "logprob": -0.007183075,
+          "special": false,
+          "text": " of"
+        },
+        {
+          "id": 5599,
+          "logprob": -0.090148926,
+          "special": false,
+          "text": " machine"
+        },
+        {
+          "id": 5168,
+          "logprob": -0.0030670166,
+          "special": false,
+          "text": " learning"
+        }
+      ],
+      "top_tokens": null
+    },
+    "generated_text": "\n\nDeep learning is a subset of machine learning"
+  },
+  {
+    "details": {
+      "best_of_sequences": null,
+      "finish_reason": "length",
+      "generated_tokens": 10,
+      "prefill": [
+        {
+          "id": 1,
+          "logprob": null,
+          "text": "<s>"
+        },
+        {
+          "id": 1824,
+          "logprob": -12.34375,
+          "text": "What"
+        },
+        {
+          "id": 349,
+          "logprob": -0.96728516,
+          "text": "is"
+        },
+        {
+          "id": 3534,
+          "logprob": -10.1796875,
+          "text": "deep"
+        },
+        {
+          "id": 5168,
+          "logprob": -0.97265625,
+          "text": "learning"
+        },
+        {
+          "id": 28804,
+          "logprob": -0.44189453,
+          "text": "?"
+        }
+      ],
+      "seed": null,
+      "tokens": [
+        {
+          "id": 13,
+          "logprob": -0.51220703,
+          "special": false,
+          "text": "\n"
+        },
+        {
+          "id": 13,
+          "logprob": -0.87402344,
+          "special": false,
+          "text": "\n"
+        },
+        {
+          "id": 23229,
+          "logprob": -0.15039062,
+          "special": false,
+          "text": "Deep"
+        },
+        {
+          "id": 5168,
+          "logprob": -0.030288696,
+          "special": false,
+          "text": " learning"
+        },
+        {
+          "id": 349,
+          "logprob": -0.1652832,
+          "special": false,
+          "text": " is"
+        },
+        {
+          "id": 264,
+          "logprob": -0.17858887,
+          "special": false,
+          "text": " a"
+        },
+        {
+          "id": 19804,
+          "logprob": -0.81103516,
+          "special": false,
+          "text": " subset"
+        },
+        {
+          "id": 302,
+          "logprob": -0.007183075,
+          "special": false,
+          "text": " of"
+        },
+        {
+          "id": 5599,
+          "logprob": -0.08880615,
+          "special": false,
+          "text": " machine"
+        },
+        {
+          "id": 5168,
+          "logprob": -0.0030612946,
+          "special": false,
+          "text": " learning"
+        }
+      ],
+      "top_tokens": null
+    },
+    "generated_text": "\n\nDeep learning is a subset of machine learning"
+  },
+  {
+    "details": {
+      "best_of_sequences": null,
+      "finish_reason": "length",
+      "generated_tokens": 10,
+      "prefill": [
+        {
+          "id": 1,
+          "logprob": null,
+          "text": "<s>"
+        },
+        {
+          "id": 1824,
+          "logprob": -12.34375,
+          "text": "What"
+        },
+        {
+          "id": 349,
+          "logprob": -0.96728516,
+          "text": "is"
+        },
+        {
+          "id": 3534,
+          "logprob": -10.1796875,
+          "text": "deep"
+        },
+        {
+          "id": 5168,
+          "logprob": -0.97265625,
+          "text": "learning"
+        },
+        {
+          "id": 28804,
+          "logprob": -0.44189453,
+          "text": "?"
+        }
+      ],
+      "seed": null,
+      "tokens": [
+        {
+          "id": 13,
+          "logprob": -0.51220703,
+          "special": false,
+          "text": "\n"
+        },
+        {
+          "id": 13,
+          "logprob": -0.87402344,
+          "special": false,
+          "text": "\n"
+        },
+        {
+          "id": 23229,
+          "logprob": -0.15039062,
+          "special": false,
+          "text": "Deep"
+        },
+        {
+          "id": 5168,
+          "logprob": -0.030288696,
+          "special": false,
+          "text": " learning"
+        },
+        {
+          "id": 349,
+          "logprob": -0.1652832,
+          "special": false,
+          "text": " is"
+        },
+        {
+          "id": 264,
+          "logprob": -0.17858887,
+          "special": false,
+          "text": " a"
+        },
+        {
+          "id": 19804,
+          "logprob": -0.81103516,
+          "special": false,
+          "text": " subset"
+        },
+        {
+          "id": 302,
+          "logprob": -0.007183075,
+          "special": false,
+          "text": " of"
+        },
+        {
+          "id": 5599,
+          "logprob": -0.08880615,
+          "special": false,
+          "text": " machine"
+        },
+        {
+          "id": 5168,
+          "logprob": -0.0030612946,
+          "special": false,
+          "text": " learning"
+        }
+      ],
+      "top_tokens": null
+    },
+    "generated_text": "\n\nDeep learning is a subset of machine learning"
+  },
+  {
+    "details": {
+      "best_of_sequences": null,
+      "finish_reason": "length",
+      "generated_tokens": 10,
+      "prefill": [
+        {
+          "id": 1,
+          "logprob": null,
+          "text": "<s>"
+        },
+        {
+          "id": 1824,
+          "logprob": -12.34375,
+          "text": "What"
+        },
+        {
+          "id": 349,
+          "logprob": -0.96728516,
+          "text": "is"
+        },
+        {
+          "id": 3534,
+          "logprob": -10.1796875,
+          "text": "deep"
+        },
+        {
+          "id": 5168,
+          "logprob": -0.97265625,
+          "text": "learning"
+        },
+        {
+          "id": 28804,
+          "logprob": -0.44189453,
+          "text": "?"
+        }
+      ],
+      "seed": null,
+      "tokens": [
+        {
+          "id": 13,
+          "logprob": -0.51220703,
+          "special": false,
+          "text": "\n"
+        },
+        {
+          "id": 13,
+          "logprob": -0.87402344,
+          "special": false,
+          "text": "\n"
+        },
+        {
+          "id": 23229,
+          "logprob": -0.15039062,
+          "special": false,
+          "text": "Deep"
+        },
+        {
+          "id": 5168,
+          "logprob": -0.030288696,
+          "special": false,
+          "text": " learning"
+        },
+        {
+          "id": 349,
+          "logprob": -0.1652832,
+          "special": false,
+          "text": " is"
+        },
+        {
+          "id": 264,
+          "logprob": -0.17858887,
+          "special": false,
+          "text": " a"
+        },
+        {
+          "id": 19804,
+          "logprob": -0.81103516,
+          "special": false,
+          "text": " subset"
+        },
+        {
+          "id": 302,
+          "logprob": -0.007183075,
+          "special": false,
+          "text": " of"
+        },
+        {
+          "id": 5599,
+          "logprob": -0.08880615,
+          "special": false,
+          "text": " machine"
+        },
+        {
+          "id": 5168,
+          "logprob": -0.0030612946,
+          "special": false,
+          "text": " learning"
+        }
+      ],
+      "top_tokens": null
+    },
+    "generated_text": "\n\nDeep learning is a subset of machine learning"
+  }
+]
diff --git a/integration-tests/models/test_flash_mixtral_awq.py b/integration-tests/models/test_flash_mixtral_awq.py
new file mode 100644
index 00000000..ab1e0f00
--- /dev/null
+++ b/integration-tests/models/test_flash_mixtral_awq.py
@@ -0,0 +1,73 @@
+import pytest
+
+
+@pytest.fixture(scope="module")
+def flash_mixtral_awq_handle(launcher):
+    with launcher("casperhansen/mixtral-instruct-awq", num_shard=2) as handle:
+        yield handle
+
+
+@pytest.fixture(scope="module")
+async def flash_mixtral_awq(flash_mixtral_awq_handle):
+    await flash_mixtral_awq_handle.health(300)
+    return flash_mixtral_awq_handle.client
+
+
+@pytest.mark.asyncio
+async def test_flash_mixtral_awq(flash_mixtral_awq, response_snapshot):
+    response = await flash_mixtral_awq.generate(
+        "What is deep learning?", max_new_tokens=10, decoder_input_details=True
+    )
+
+    assert response.details.generated_tokens == 10
+    assert (
+        response.generated_text == "\n\nDeep learning is a subset of machine learning"
+    )
+    assert response == response_snapshot
+
+
+@pytest.mark.asyncio
+async def test_flash_mixtral_awq_all_params(flash_mixtral_awq, response_snapshot):
+    response = await flash_mixtral_awq.generate(
+        "What is deep learning?",
+        max_new_tokens=10,
+        repetition_penalty=1.2,
+        return_full_text=True,
+        stop_sequences=["test"],
+        temperature=0.5,
+        top_p=0.9,
+        top_k=10,
+        truncate=5,
+        typical_p=0.9,
+        watermark=True,
+        decoder_input_details=True,
+        seed=0,
+    )
+
+    assert response.details.generated_tokens == 10
+    assert (
+        response.generated_text
+        == "What is deep learning?\nDeep Learning is a subset of Machine Learning,"
+    )
+    assert response == response_snapshot
+
+
+@pytest.mark.asyncio
+async def test_flash_mixtral_awq_load(
+    flash_mixtral_awq, generate_load, response_snapshot
+):
+    responses = await generate_load(
+        flash_mixtral_awq, "What is deep learning?", max_new_tokens=10, n=4
+    )
+
+    assert len(responses) == 4
+    assert responses[0].details.generated_tokens == 10
+    assert (
+        responses[0].generated_text
+        == "\n\nDeep learning is a subset of machine learning"
+    )
+    assert all(
+        [r.generated_text == responses[0].generated_text for r in responses]
+    ), f"{[r.generated_text  for r in responses]}"
+
+    assert responses == response_snapshot