diff --git a/README.md b/README.md
index 53c43c2..f6d727c 100644
--- a/README.md
+++ b/README.md
@@ -20,6 +20,7 @@ Python 3 and C++ compiler required. The command will download the model and the
 | Llama 3 8B Instruct Q40     | Chat, API | 6.32 GB  | `python launch.py llama3_8b_instruct_q40`     |
 | Llama 3.1 8B Instruct Q40   | Chat, API | 6.32 GB  | `python launch.py llama3_1_8b_instruct_q40`   |
 | Llama 3.1 405B Instruct Q40 | Chat, API | 238 GB   | `python launch.py llama3_1_405b_instruct_q40` |
+| Llama 3.2 1B Instruct Q40   | Chat, API | 1.7 GB   | `python launch.py llama3_2_1b_instruct_q40`   |
 
 ### 🛠️ Convert Model Manually
 
diff --git a/launch.py b/launch.py
index 364923f..469704f 100644
--- a/launch.py
+++ b/launch.py
@@ -37,6 +37,11 @@ def parts(length):
         'https://huggingface.co/b4rtaz/Llama-3_1-405B-Q40-Instruct-Distributed-Llama/resolve/main/dllama_tokenizer_llama_3_1.t?download=true',
         'q40', 'q80', 'chat'
     ],
+    'llama3_2_1b_instruct_q40': [
+        ['https://huggingface.co/b4rtaz/Llama-3_2-1B-Q40-Instruct-Distributed-Llama/resolve/main/dllama_model_llama3.2-1b-instruct_q40.m?download=true'],
+        'https://huggingface.co/b4rtaz/Llama-3_2-1B-Q40-Instruct-Distributed-Llama/resolve/main/dllama_tokenizer_llama3_2.t?download=true',
+        'q40', 'q80', 'chat', '--max-seq-len 8192'
+    ],
 }
 
 def downloadFile(urls: str, path: str):
@@ -107,6 +112,8 @@ def printUsage():
     else:
         command = './dllama inference --steps 64 --prompt "Hello world"'
     command += f' --model {modelPath} --tokenizer {tokenizerPath} --buffer-float-type {model[3]} --nthreads 4'
+    if (len(model) > 5):
+        command += f' {model[5]}'
 
     print('To run Distributed Llama you need to execute:')
     print('--- copy start ---')