diff --git a/settings-docker.yaml b/settings-docker.yaml
index c68da41..3d78ff7 100644
--- a/settings-docker.yaml
+++ b/settings-docker.yaml
@@ -9,8 +9,8 @@ embedding:
   mode: ${PGPT_MODE:sagemaker}
 
 llamacpp:
-  llm_hf_repo_id: ${PGPT_HF_REPO_ID:TheBloke/Mistral-7B-Instruct-v0.1-GGUF}
-  llm_hf_model_file: ${PGPT_HF_MODEL_FILE:mistral-7b-instruct-v0.1.Q4_K_M.gguf}
+  llm_hf_repo_id: ${PGPT_HF_REPO_ID:lmstudio-community/Meta-Llama-3.1-8B-Instruct-GGUF}
+  llm_hf_model_file: ${PGPT_HF_MODEL_FILE:Meta-Llama-3.1-8B-Instruct-Q4_K_M.gguf}
 
 huggingface:
   embedding_hf_model_name: ${PGPT_EMBEDDING_HF_MODEL_NAME:BAAI/bge-small-en-v1.5}
diff --git a/settings-local.yaml b/settings-local.yaml
index 48eeb0e..596d7bc 100644
--- a/settings-local.yaml
+++ b/settings-local.yaml
@@ -7,12 +7,12 @@ llm:
   # Should be matching the selected model
   max_new_tokens: 512
   context_window: 3900
-  tokenizer: mistralai/Mistral-7B-Instruct-v0.2
-  prompt_style: "mistral"
+  tokenizer: meta-llama/Meta-Llama-3.1-8B-Instruct
+  prompt_style: "llama3"
 
 llamacpp:
-  llm_hf_repo_id: TheBloke/Mistral-7B-Instruct-v0.2-GGUF
-  llm_hf_model_file: mistral-7b-instruct-v0.2.Q4_K_M.gguf
+  llm_hf_repo_id: lmstudio-community/Meta-Llama-3.1-8B-Instruct-GGUF
+  llm_hf_model_file: Meta-Llama-3.1-8B-Instruct-Q4_K_M.gguf
 
 embedding:
   mode: huggingface
diff --git a/settings-vllm.yaml b/settings-vllm.yaml
index 1bfab6b..db4ef75 100644
--- a/settings-vllm.yaml
+++ b/settings-vllm.yaml
@@ -4,7 +4,7 @@ server:
 llm:
   mode: openailike
   max_new_tokens: 512
-  tokenizer: mistralai/Mistral-7B-Instruct-v0.2
+  tokenizer: meta-llama/Meta-Llama-3.1-8B-Instruct
   temperature: 0.1
 
 embedding:
diff --git a/settings.yaml b/settings.yaml
index 935defc..3f7a989 100644
--- a/settings.yaml
+++ b/settings.yaml
@@ -36,12 +36,12 @@ ui:
 
 llm:
   mode: llamacpp
-  prompt_style: "mistral"
+  prompt_style: "llama3"
   # Should be matching the selected model
   max_new_tokens: 512
   context_window: 3900
   # Select your tokenizer. Llama-index tokenizer is the default.
-  # tokenizer: mistralai/Mistral-7B-Instruct-v0.2
+  # tokenizer: meta-llama/Meta-Llama-3.1-8B-Instruct
   temperature: 0.1      # The temperature of the model. Increasing the temperature will make the model answer more creatively. A value of 0.1 would be more factual. (Default: 0.1)
 
 rag:
@@ -62,8 +62,8 @@ clickhouse:
     database: embeddings
 
 llamacpp:
-  llm_hf_repo_id: TheBloke/Mistral-7B-Instruct-v0.2-GGUF
-  llm_hf_model_file: mistral-7b-instruct-v0.2.Q4_K_M.gguf
+  llm_hf_repo_id: lmstudio-community/Meta-Llama-3.1-8B-Instruct-GGUF
+  llm_hf_model_file: Meta-Llama-3.1-8B-Instruct-Q4_K_M.gguf
   tfs_z: 1.0            # Tail free sampling is used to reduce the impact of less probable tokens from the output. A higher value (e.g., 2.0) will reduce the impact more, while a value of 1.0 disables this setting
   top_k: 40             # Reduces the probability of generating nonsense. A higher value (e.g. 100) will give more diverse answers, while a lower value (e.g. 10) will be more conservative. (Default: 40)
   top_p: 1.0            # Works together with top-k. A higher value (e.g., 0.95) will lead to more diverse text, while a lower value (e.g., 0.5) will generate more focused and conservative text. (Default: 0.9)