add glm-47 and deepseek-v32

src/exo/shared/models/model_cards.py

@@ -70,34 +70,36 @@ MODEL_CARDS: dict[str, ModelCard] = {
             supports_tensor=True,
         ),
     ),
-    # "deepseek-v3.2": ModelCard(
-    #     short_id="deepseek-v3.2",
-    #     model_id=ModelId("mlx-community/DeepSeek-V3.2-8bit"),
-    #     name="DeepSeek V3.2 (8-bit)",
-    #     description="""DeepSeek V3.2 is a large language model trained on the DeepSeek V3.2 dataset.""",
-    #     tags=[],
-    #     metadata=ModelMetadata(
-    #         model_id=ModelId("mlx-community/DeepSeek-V3.2-8bit"),
-    #         pretty_name="DeepSeek V3.2 (8-bit)",
-    #         storage_size=Memory.from_kb(754706307),
-    #         n_layers=61,
-    #         hidden_size=7168,
-    #     ),
-    # ),
-    # "deepseek-v3.2-4bit": ModelCard(
-    #     short_id="deepseek-v3.2-4bit",
-    #     model_id=ModelId("mlx-community/DeepSeek-V3.2-4bit"),
-    #     name="DeepSeek V3.2 (4-bit)",
-    #     description="""DeepSeek V3.2 is a large language model trained on the DeepSeek V3.2 dataset.""",
-    #     tags=[],
-    #     metadata=ModelMetadata(
-    #         model_id=ModelId("mlx-community/DeepSeek-V3.2-4bit"),
-    #         pretty_name="DeepSeek V3.2 (4-bit)",
-    #         storage_size=Memory.from_kb(754706307 // 2),  # TODO !!!!!
-    #         n_layers=61,
-    #         hidden_size=7168,
-    #     ),
-    # ),
+    "deepseek-v3.2": ModelCard(
+        short_id="deepseek-v3.2",
+        model_id=ModelId("mlx-community/DeepSeek-V3.2-8bit"),
+        name="DeepSeek V3.2 (8-bit)",
+        description="""DeepSeek V3.2 is a large language model trained on the DeepSeek V3.2 dataset.""",
+        tags=[],
+        metadata=ModelMetadata(
+            model_id=ModelId("mlx-community/DeepSeek-V3.2-8bit"),
+            pretty_name="DeepSeek V3.2 (8-bit)",
+            storage_size=Memory.from_kb(754706307),
+            n_layers=61,
+            hidden_size=7168,
+            supports_tensor=True,
+        ),
+    ),
+    "deepseek-v3.2-4bit": ModelCard(
+        short_id="deepseek-v3.2-4bit",
+        model_id=ModelId("mlx-community/DeepSeek-V3.2-4bit"),
+        name="DeepSeek V3.2 (4-bit)",
+        description="""DeepSeek V3.2 is a large language model trained on the DeepSeek V3.2 dataset.""",
+        tags=[],
+        metadata=ModelMetadata(
+            model_id=ModelId("mlx-community/DeepSeek-V3.2-4bit"),
+            pretty_name="DeepSeek V3.2 (4-bit)",
+            storage_size=Memory.from_kb(754706307 // 2),  # TODO !!!!!
+            n_layers=61,
+            hidden_size=7168,
+            supports_tensor=True,
+        ),
+    ),
     # deepseek r1
     # "deepseek-r1-0528-4bit": ModelCard(
     #     short_id="deepseek-r1-0528-4bit",
@@ -554,6 +556,36 @@ MODEL_CARDS: dict[str, ModelCard] = {
             supports_tensor=True,
         ),
     ),
+    "glm-4.7-4bit": ModelCard(
+        short_id="glm-4.7-4bit",
+        model_id=ModelId("mlx-community/GLM-4.7-4bit"),
+        name="GLM 4.7 4bit",
+        description="GLM 4.7 4bit",
+        tags=[],
+        metadata=ModelMetadata(
+            model_id=ModelId("mlx-community/GLM-4.7-4bit"),
+            pretty_name="GLM 4.7 4bit",
+            storage_size=Memory.from_bytes(198556925568),
+            n_layers=91,
+            hidden_size=5120,
+            supports_tensor=True,
+        ),
+    ),
+    "glm-4.7-8bit-gs32": ModelCard(
+        short_id="glm-4.7-8bit-gs32",
+        model_id=ModelId("mlx-community/GLM-4.7-8bit-gs32"),
+        name="GLM 4.7 8bit (gs32)",
+        description="GLM 4.7 8bit (gs32)",
+        tags=[],
+        metadata=ModelMetadata(
+            model_id=ModelId("mlx-community/GLM-4.7-8bit-gs32"),
+            pretty_name="GLM 4.7 8bit (gs32)",
+            storage_size=Memory.from_bytes(396963397248),
+            n_layers=91,
+            hidden_size=5120,
+            supports_tensor=True,
+        ),
+    ),
     # "devstral-2-123b-instruct-2512-8bit": ModelCard(
     #     short_id="devstral-2-123b-instruct-2512-8bit",
     #     model_id=ModelId("mlx-community/Devstral-2-123B-Instruct-2512-8bit"),

tests/headless_runner.py

@@ -89,6 +89,10 @@ async def assert_downloads():
     await sd.ensure_shard(
         await build_full_shard(MODEL_CARDS["gpt-oss-20b-4bit"].model_id)
     )
+    await sd.ensure_shard(await build_full_shard(MODEL_CARDS["deepseek-v3.2"].model_id))
+    await sd.ensure_shard(
+        await build_full_shard(MODEL_CARDS["glm-4.7-8bit-gs32"].model_id)
+    )
 
 
 async def ring_backend(test: Tests):