← back to Exo
model-cards: add missing metadata for Qwen3 Coder Next variants (#1576)
71e48c0f627b125b56e56c04e7a8eddd50a194f6 · 2026-02-20 18:25:49 +0000 · Jake Hillion
The Qwen3-Coder-Next model card TOML files were missing family,
quantization, base_model, and capabilities fields. This caused them not
to appear under the Qwen family filter in the dashboard's model picker.
Added the missing metadata to all five variants (4bit, 5bit, 6bit, 8bit,
bf16), matching the format used by the existing Qwen3-Coder-480B model
cards.
Test plan:
- Eyeballs
Files touched
M resources/inference_model_cards/mlx-community--Qwen3-Coder-Next-4bit.tomlM resources/inference_model_cards/mlx-community--Qwen3-Coder-Next-5bit.tomlM resources/inference_model_cards/mlx-community--Qwen3-Coder-Next-6bit.tomlM resources/inference_model_cards/mlx-community--Qwen3-Coder-Next-8bit.tomlM resources/inference_model_cards/mlx-community--Qwen3-Coder-Next-bf16.toml
Diff
commit 71e48c0f627b125b56e56c04e7a8eddd50a194f6
Author: Jake Hillion <jake@hillion.co.uk>
Date: Fri Feb 20 18:25:49 2026 +0000
model-cards: add missing metadata for Qwen3 Coder Next variants (#1576)
The Qwen3-Coder-Next model card TOML files were missing family,
quantization, base_model, and capabilities fields. This caused them not
to appear under the Qwen family filter in the dashboard's model picker.
Added the missing metadata to all five variants (4bit, 5bit, 6bit, 8bit,
bf16), matching the format used by the existing Qwen3-Coder-480B model
cards.
Test plan:
- Eyeballs
---
.../inference_model_cards/mlx-community--Qwen3-Coder-Next-4bit.toml | 4 ++++
.../inference_model_cards/mlx-community--Qwen3-Coder-Next-5bit.toml | 4 ++++
.../inference_model_cards/mlx-community--Qwen3-Coder-Next-6bit.toml | 4 ++++
.../inference_model_cards/mlx-community--Qwen3-Coder-Next-8bit.toml | 4 ++++
.../inference_model_cards/mlx-community--Qwen3-Coder-Next-bf16.toml | 4 ++++
5 files changed, 20 insertions(+)
diff --git a/resources/inference_model_cards/mlx-community--Qwen3-Coder-Next-4bit.toml b/resources/inference_model_cards/mlx-community--Qwen3-Coder-Next-4bit.toml
index 9e6d3511..5f494594 100644
--- a/resources/inference_model_cards/mlx-community--Qwen3-Coder-Next-4bit.toml
+++ b/resources/inference_model_cards/mlx-community--Qwen3-Coder-Next-4bit.toml
@@ -3,6 +3,10 @@ n_layers = 48
hidden_size = 2048
supports_tensor = true
tasks = ["TextGeneration"]
+family = "qwen"
+quantization = "4bit"
+base_model = "Qwen3 Coder Next"
+capabilities = ["text", "code"]
[storage_size]
in_bytes = 45644286500
diff --git a/resources/inference_model_cards/mlx-community--Qwen3-Coder-Next-5bit.toml b/resources/inference_model_cards/mlx-community--Qwen3-Coder-Next-5bit.toml
index ebf487af..60a5f131 100644
--- a/resources/inference_model_cards/mlx-community--Qwen3-Coder-Next-5bit.toml
+++ b/resources/inference_model_cards/mlx-community--Qwen3-Coder-Next-5bit.toml
@@ -3,6 +3,10 @@ n_layers = 48
hidden_size = 2048
supports_tensor = true
tasks = ["TextGeneration"]
+family = "qwen"
+quantization = "5bit"
+base_model = "Qwen3 Coder Next"
+capabilities = ["text", "code"]
[storage_size]
in_bytes = 57657697020
diff --git a/resources/inference_model_cards/mlx-community--Qwen3-Coder-Next-6bit.toml b/resources/inference_model_cards/mlx-community--Qwen3-Coder-Next-6bit.toml
index ef801631..59ede911 100644
--- a/resources/inference_model_cards/mlx-community--Qwen3-Coder-Next-6bit.toml
+++ b/resources/inference_model_cards/mlx-community--Qwen3-Coder-Next-6bit.toml
@@ -3,6 +3,10 @@ n_layers = 48
hidden_size = 2048
supports_tensor = true
tasks = ["TextGeneration"]
+family = "qwen"
+quantization = "6bit"
+base_model = "Qwen3 Coder Next"
+capabilities = ["text", "code"]
[storage_size]
in_bytes = 68899327465
diff --git a/resources/inference_model_cards/mlx-community--Qwen3-Coder-Next-8bit.toml b/resources/inference_model_cards/mlx-community--Qwen3-Coder-Next-8bit.toml
index 05b92116..1e8b0f12 100644
--- a/resources/inference_model_cards/mlx-community--Qwen3-Coder-Next-8bit.toml
+++ b/resources/inference_model_cards/mlx-community--Qwen3-Coder-Next-8bit.toml
@@ -3,6 +3,10 @@ n_layers = 48
hidden_size = 2048
supports_tensor = true
tasks = ["TextGeneration"]
+family = "qwen"
+quantization = "8bit"
+base_model = "Qwen3 Coder Next"
+capabilities = ["text", "code"]
[storage_size]
in_bytes = 89357758772
diff --git a/resources/inference_model_cards/mlx-community--Qwen3-Coder-Next-bf16.toml b/resources/inference_model_cards/mlx-community--Qwen3-Coder-Next-bf16.toml
index 93798231..5db8fae9 100644
--- a/resources/inference_model_cards/mlx-community--Qwen3-Coder-Next-bf16.toml
+++ b/resources/inference_model_cards/mlx-community--Qwen3-Coder-Next-bf16.toml
@@ -3,6 +3,10 @@ n_layers = 48
hidden_size = 2048
supports_tensor = true
tasks = ["TextGeneration"]
+family = "qwen"
+quantization = "bf16"
+base_model = "Qwen3 Coder Next"
+capabilities = ["text", "code"]
[storage_size]
in_bytes = 157548627945
← 42da58c2 worker: add EXO_MODELS_PATH for pre-downloaded model directo
·
back to Exo
·
downloads: add read_only flag to DownloadCompleted for EXO_M ab9273e7 →