diff --git a/recipes/configs/gemma/evaluation.yaml b/recipes/configs/gemma/evaluation.yaml
new file mode 100644
index 0000000000..2ff8f78546
--- /dev/null
+++ b/recipes/configs/gemma/evaluation.yaml
@@ -0,0 +1,39 @@
+# Config for EleutherEvalRecipe in eleuther_eval.py
+#
+# To launch, run the following command:
+#    tune run eleuther_eval --config gemma/evaluation
+
+# Model Arguments
+model:
+  _component_: torchtune.models.gemma.gemma_2b
+
+# Checkpointer
+checkpointer:
+  _component_: torchtune.training.FullModelHFCheckpointer
+  checkpoint_dir: /tmp/gemma-2b
+  checkpoint_files: [
+    model-00001-of-00002.safetensors,
+    model-00002-of-00002.safetensors,
+  ]
+  output_dir: ./ # Not needed
+  model_type: GEMMA
+
+# Tokenizer
+tokenizer:
+  _component_: torchtune.models.gemma.gemma_tokenizer
+  path: /tmp/gemma-2b/tokenizer.model
+
+# Environment
+device: cuda
+dtype: bf16
+seed: 1234 # It is not recommended to change this seed, b/c it matches EleutherAI's default seed
+
+# EleutherAI specific eval args
+tasks: ["truthfulqa_mc2"]
+limit: null
+max_seq_length: 4096
+batch_size: 8
+enable_kv_cache: True
+
+# Quantization specific args
+quantizer: null
diff --git a/torchtune/_recipe_registry.py b/torchtune/_recipe_registry.py
index ca1ce6150e..30ba7b3c81 100644
--- a/torchtune/_recipe_registry.py
+++ b/torchtune/_recipe_registry.py
@@ -328,6 +328,10 @@ class Recipe:
                 name="qwen2/evaluation",
                 file_path="qwen2/evaluation.yaml",
             ),
+            Config(
+                name="gemma/evaluation",
+                file_path="gemma/evaluation.yaml",
+            ),
         ],
         supports_distributed=False,
     ),