diff --git a/forge/test/models/pytorch/multimodal/deepseek/test_deepseek_math.py b/forge/test/models/pytorch/multimodal/deepseek/test_deepseek_math.py
new file mode 100644
index 000000000..af77ec04c
--- /dev/null
+++ b/forge/test/models/pytorch/multimodal/deepseek/test_deepseek_math.py
@@ -0,0 +1,86 @@
+# SPDX-FileCopyrightText: (c) 2025 Tenstorrent AI ULC
+#
+# SPDX-License-Identifier: Apache-2.0
+import pytest
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer, GenerationConfig
+
+import forge
+
+from test.models.utils import Framework, Source, Task, build_module_name
+
+
+def generation(max_new_tokens, compiled_model, input_ids, tokenizer):
+    for i in range(max_new_tokens):
+        logits = compiled_model(input_ids)
+        next_token_logits = logits[:, -1, :]
+        next_token_id = torch.argmax(next_token_logits, dim=-1)
+
+        if next_token_id == tokenizer.eos_token_id:
+            break
+
+        input_ids = torch.cat([input_ids, next_token_id.unsqueeze(0)], dim=-1)
+
+    generated_text = tokenizer.decode(input_ids[0], skip_special_tokens=True)
+    return generated_text
+
+
+def download_model_and_tokenizer(model_name):
+    tokenizer = AutoTokenizer.from_pretrained(model_name)
+    model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="cpu")
+    model.generation_config = GenerationConfig.from_pretrained(model_name)
+    model.generation_config.pad_token_id = model.generation_config.eos_token_id
+    model.generation_config.use_cache = False
+
+    # Prepare input sentence
+    messages = [
+        {
+            "role": "user",
+            "content": "what is the integral of x^2 from 0 to 2?\nPlease reason step by step, and put your final answer within \\boxed{}.",
+        }
+    ]
+    input_ids = tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt")
+    return model, tokenizer, input_ids
+
+
+class Wrapper(torch.nn.Module):
+    def __init__(self, model):
+        super().__init__()
+        self.model = model
+
+    def forward(self, input_tensor):
+        return self.model(input_tensor, max_new_tokens=100).logits
+
+
+@pytest.mark.parametrize("variant", ["deepseek-math-7b-instruct"])
+def test_deepseek_inference_no_cache_cpu(variant):
+    model_name = f"deepseek-ai/{variant}"
+    model, tokenizer, input_ids = download_model_and_tokenizer(model_name)
+
+    framework_model = Wrapper(model)
+
+    generated_text = generation(
+        max_new_tokens=100, compiled_model=framework_model, input_ids=input_ids, tokenizer=tokenizer
+    )
+    print(generated_text)
+
+
+@pytest.mark.parametrize("variant", ["deepseek-math-7b-instruct"])
+def test_deepseek_inference(record_forge_property, variant):
+    # Build Module Name
+    module_name = build_module_name(
+        framework=Framework.PYTORCH, model="deepseek", variant=variant, task=Task.QA, source=Source.HUGGINGFACE
+    )
+
+    # Record Forge Property
+    record_forge_property("model_name", module_name)
+
+    model_name = f"deepseek-ai/{variant}"
+    model, tokenizer, input_ids = download_model_and_tokenizer(model_name)
+    framework_model = Wrapper(model)
+
+    compiled_model = forge.compile(framework_model, sample_inputs=[input_ids], module_name=module_name)
+    generated_text = generation(
+        max_new_tokens=1, compiled_model=compiled_model, input_ids=input_ids, tokenizer=tokenizer
+    )
+    print(generated_text)