Sub 1B models ? - What wind.surf will do ?

app.py

@@ -4,18 +4,14 @@ import requests
 
 # Define available models
 MODELS = {
-    "Llama-3.2-3B": {
-        "repo_id": "lmstudio-community/Llama-3.2-3B-Instruct-GGUF",
-        "filename": "*Q4_K_M.gguf",
-        "chat_format": "chatml"
-    },
-    "Llama-3.2-5B": {
-        "repo_id": "lmstudio-community/Llama-3.2-1B-Instruct-GGUF",
+    # 3B+ Models
+    "Phi-3.5-mini-4B": {
+        "repo_id": "bartowski/Phi-3.5-mini-instruct-GGUF",
         "filename": "*Q4_K_M.gguf",
         "chat_format": "chatml"
-    },
-    "Phi-3.5-mini": {
-        "repo_id": "bartowski/Phi-3.5-mini-instruct-GGUF",
+    },    
+    "Llama-3.2-3B": {
+        "repo_id": "lmstudio-community/Llama-3.2-3B-Instruct-GGUF",
         "filename": "*Q4_K_M.gguf",
         "chat_format": "chatml"
     },
@@ -29,6 +25,11 @@ MODELS = {
         "filename": "*Q4_K_M.gguf",
         "chat_format": "chatml"
     },
+    "Gemma-2B": {
+        "repo_id": "lmstudio-community/gemma-2-2b-it-GGUF",
+        "filename": "*Q4_K_M.gguf",
+        "chat_format": "chatml"
+    },
     "SmolLM2-1.7B": {
         "repo_id": "HuggingFaceTB/SmolLM2-1.7B-Instruct-GGUF",
         "filename": "*Q4_K_M.gguf",
@@ -39,13 +40,50 @@ MODELS = {
         "filename": "*Q4_K_M.gguf",
         "chat_format": "chatml"
     },
+    "Llama-3.2-1B": {
+        "repo_id": "lmstudio-community/Llama-3.2-1B-Instruct-GGUF",
+        "filename": "*Q4_K_M.gguf",
+        "chat_format": "chatml"
+    },    
+    "AMD-OLMo-1B": {
+        "repo_id": "lmstudio-community/AMD-OLMo-1B-SFT-GGUF",
+        "filename": "*Q4_K_M.gguf",
+        "chat_format": "chatml"
+    },
+    "AMD-OLMo-1B-DPO": {
+        "repo_id": "lmstudio-community/AMD-OLMo-1B-SFT-DPO-GGUF",
+        "filename": "*Q4_K_M.gguf",
+        "chat_format": "chatml"
+    },
     "Granite-1B": {
         "repo_id": "lmstudio-community/granite-3.0-1b-a400m-instruct-GGUF",
         "filename": "*Q4_K_M.gguf",
         "chat_format": "chatml"
     },
-    "AMD-OLMo-1B": {
-        "repo_id": "lmstudio-community/AMD-OLMo-1B-SFT-GGUF",
+    
+    # Sub-1B Models
+    "MobileLLM-600M": {
+        "repo_id": "pjh64/MobileLLM-600M-GGUF",
+        "filename": "*Q4_K_M.gguf",
+        "chat_format": "chatml"
+    },
+    "Danube-500M": {
+        "repo_id": "BoscoTheDog/Danube_3-500M_Chat_GGUF",
+        "filename": "*Q4_K_M.gguf",
+        "chat_format": "chatml"
+    },
+    "Qwen2.5-500M": {
+        "repo_id": "Qwen/Qwen2.5-0.5B-Instruct-GGUF",
+        "filename": "*Q4_K_M.gguf",
+        "chat_format": "chatml"
+    },
+    "MobileLLM-350M": {
+        "repo_id": "pjh64/MobileLLM-350M-GGUF",
+        "filename": "*Q4_K_M.gguf",
+        "chat_format": "chatml"
+    },
+    "MobileLLM-125M": {
+        "repo_id": "pjh64/MobileLLM-125M-GGUF",
         "filename": "*Q4_K_M.gguf",
         "chat_format": "chatml"
     }

models.lst

@@ -6,6 +6,8 @@ https://huggingface.co/lmstudio-community/granite-3.0-3b-a800m-instruct-GGUF
 
 https://huggingface.co/lmstudio-community/Qwen2.5-3B-Instruct-GGUF
 
+https://huggingface.co/lmstudio-community/gemma-2-2b-it-GGUF
+
 https://huggingface.co/HuggingFaceTB/SmolLM2-1.7B-Instruct-GGUF
 
 https://huggingface.co/lmstudio-community/Qwen2.5-1.5B-Instruct-GGUF
@@ -14,4 +16,13 @@ https://huggingface.co/lmstudio-community/granite-3.0-1b-a400m-instruct-GGUF
 
 https://huggingface.co/lmstudio-community/AMD-OLMo-1B-SFT-DPO-GGUF
 
+https://huggingface.co/pjh64/MobileLLM-600M-GGUF
+
+https://huggingface.co/BoscoTheDog/Danube_3-500M_Chat_GGUF
+
+https://huggingface.co/Qwen/Qwen2.5-0.5B-Instruct-GGUF
+
+https://huggingface.co/pjh64/MobileLLM-350M-GGUF
+
+https://huggingface.co/pjh64/MobileLLM-125M-GGUF