← back to Exo
model_cards.py: clean up commented out code
e0aab46fd8f3c741ba57d6507f828b216efd3d8d · 2026-01-15 11:58:13 +0000 · Jake Hillion
Clean up the commented out code and make sure the comments are unified.
Carrying around the commented out code means people making changes to
model_cards are supposed to update it, but that's not clear and won't be
picked up by type checking etc. Drop it for now - it's in the git
history.
Also make the rest of the comments a bit more uniform, and place
comments about a specific model card inside the model card (instead of
above) so they don't get lost when code is added/moved around.
Test plan:
- my eyes
Files touched
M src/exo/shared/models/model_cards.py
Diff
commit e0aab46fd8f3c741ba57d6507f828b216efd3d8d
Author: Jake Hillion <jake@hillion.co.uk>
Date: Thu Jan 15 11:58:13 2026 +0000
model_cards.py: clean up commented out code
Clean up the commented out code and make sure the comments are unified.
Carrying around the commented out code means people making changes to
model_cards are supposed to update it, but that's not clear and won't be
picked up by type checking etc. Drop it for now - it's in the git
history.
Also make the rest of the comments a bit more uniform, and place
comments about a specific model card inside the model card (instead of
above) so they don't get lost when code is added/moved around.
Test plan:
- my eyes
---
src/exo/shared/models/model_cards.py | 105 ++---------------------------------
1 file changed, 4 insertions(+), 101 deletions(-)
diff --git a/src/exo/shared/models/model_cards.py b/src/exo/shared/models/model_cards.py
index d46a8115..18768135 100644
--- a/src/exo/shared/models/model_cards.py
+++ b/src/exo/shared/models/model_cards.py
@@ -14,32 +14,6 @@ class ModelCard(CamelCaseModel):
MODEL_CARDS: dict[str, ModelCard] = {
# deepseek v3
- # "deepseek-v3-0324:4bit": ModelCard(
- # short_id="deepseek-v3-0324:4bit",
- # model_id="mlx-community/DeepSeek-V3-0324-4bit",
- # name="DeepSeek V3 0324 (4-bit)",
- # description="""DeepSeek V3 is a large language model trained on the DeepSeek V3 dataset.""",
- # tags=[],
- # metadata=ModelMetadata(
- # model_id=ModelId("mlx-community/DeepSeek-V3-0324-4bit"),
- # pretty_name="DeepSeek V3 0324 (4-bit)",
- # storage_size=Memory.from_kb(409706307),
- # n_layers=61,
- # ),
- # ),
- # "deepseek-v3-0324": ModelCard(
- # short_id="deepseek-v3-0324",
- # model_id="mlx-community/DeepSeek-v3-0324-8bit",
- # name="DeepSeek V3 0324 (8-bit)",
- # description="""DeepSeek V3 is a large language model trained on the DeepSeek V3 dataset.""",
- # tags=[],
- # metadata=ModelMetadata(
- # model_id=ModelId("mlx-community/DeepSeek-v3-0324-8bit"),
- # pretty_name="DeepSeek V3 0324 (8-bit)",
- # storage_size=Memory.from_kb(754706307),
- # n_layers=61,
- # ),
- # ),
"deepseek-v3.1-4bit": ModelCard(
short_id="deepseek-v3.1-4bit",
model_id=ModelId("mlx-community/DeepSeek-V3.1-4bit"),
@@ -70,65 +44,6 @@ 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,
- # 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",
- # model_id="mlx-community/DeepSeek-R1-0528-4bit",
- # name="DeepSeek-R1-0528 (4-bit)",
- # description="""DeepSeek R1 is a large language model trained on the DeepSeek R1 dataset.""",
- # tags=[],
- # metadata=ModelMetadata(
- # model_id=ModelId("mlx-community/DeepSeek-R1-0528-4bit"),
- # pretty_name="DeepSeek R1 671B (4-bit)",
- # storage_size=Memory.from_kb(409706307),
- # n_layers=61,
- # hidden_size=7168,
- # ),
- # ),
- # "deepseek-r1-0528": ModelCard(
- # short_id="deepseek-r1-0528",
- # model_id="mlx-community/DeepSeek-R1-0528-8bit",
- # name="DeepSeek-R1-0528 (8-bit)",
- # description="""DeepSeek R1 is a large language model trained on the DeepSeek R1 dataset.""",
- # tags=[],
- # metadata=ModelMetadata(
- # model_id=ModelId("mlx-community/DeepSeek-R1-0528-8bit"),
- # pretty_name="DeepSeek R1 671B (8-bit)",
- # storage_size=Memory.from_bytes(754998771712),
- # n_layers=61,
- # . hidden_size=7168,
- # ),
- # ),
# kimi k2
"kimi-k2-instruct-4bit": ModelCard(
short_id="kimi-k2-instruct-4bit",
@@ -525,8 +440,9 @@ MODEL_CARDS: dict[str, ModelCard] = {
supports_tensor=True,
),
),
- # Needs to be quantized g32 or g16.
+ # glm 4.5
"glm-4.5-air-8bit": ModelCard(
+ # Needs to be quantized g32 or g16 to work with tensor parallel
short_id="glm-4.5-air-8bit",
model_id=ModelId("mlx-community/GLM-4.5-Air-8bit"),
name="GLM 4.5 Air 8bit",
@@ -556,6 +472,7 @@ MODEL_CARDS: dict[str, ModelCard] = {
supports_tensor=True,
),
),
+ # glm 4.7
"glm-4.7-4bit": ModelCard(
short_id="glm-4.7-4bit",
model_id=ModelId("mlx-community/GLM-4.7-4bit"),
@@ -601,6 +518,7 @@ MODEL_CARDS: dict[str, ModelCard] = {
supports_tensor=True,
),
),
+ # minimax-m2
"minimax-m2.1-8bit": ModelCard(
short_id="minimax-m2.1-8bit",
model_id=ModelId("mlx-community/MiniMax-M2.1-8bit"),
@@ -631,19 +549,4 @@ MODEL_CARDS: dict[str, ModelCard] = {
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"),
- # name="Devstral 2 123B Instruct 2512 (8-bit, MLX)",
- # description="""Mistral AI's Devstral 2 123B Instruct (2512) is an agentic coding model.""",
- # tags=[],
- # metadata=ModelMetadata(
- # model_id=ModelId("mlx-community/Devstral-2-123B-Instruct-2512-8bit"),
- # pretty_name="Devstral 2 123B Instruct 2512 (8-bit, MLX)",
- # storage_size=Memory.from_kb(133_000_000),
- # n_layers=88,
- # hidden_size=12288,
- # supports_tensor=True,
- # ),
- # ),
}
← 82ba42ba add glm-47, minimax-m21 (#1147)
·
back to Exo
·
rust: remove dead code 4bc4d506 →