feat(providers): add Rapid-MLX provider

providers/rapid-mlx/models/mlx-community/Qwen3-0.6B-4bit.toml

@@ -0,0 +1,21 @@
+name = "Qwen3 0.6B 4bit"
+family = "qwen"
+release_date = "2025-04-28"
+last_updated = "2025-04-28"
+attachment = false
+reasoning = true
+temperature = true
+tool_call = true
+open_weights = true
+
+[cost]
+input = 0
+output = 0
+
+[limit]
+context = 40_960
+output = 16_384
+
+[modalities]
+input = ["text"]
+output = ["text"]

providers/rapid-mlx/models/mlx-community/Qwen3.5-4B-MLX-4bit.toml

@@ -0,0 +1,21 @@
+name = "Qwen3.5 4B MLX 4bit"
+family = "qwen"
+release_date = "2026-03-02"
+last_updated = "2026-03-02"
+attachment = false
+reasoning = false
+temperature = true
+tool_call = true
+open_weights = true
+
+[cost]
+input = 0
+output = 0
+
+[limit]
+context = 262_144
+output = 32_768
+
+[modalities]
+input = ["text"]
+output = ["text"]

providers/rapid-mlx/models/mlx-community/gemma-4-26b-a4b-it-4bit.toml

@@ -0,0 +1,21 @@
+name = "Gemma 4 26B A4B Instruct 4bit"
+family = "gemma"
+release_date = "2026-04-02"
+last_updated = "2026-04-03"
+attachment = false
+reasoning = false
+temperature = true
+tool_call = true
+open_weights = true
+
+[cost]
+input = 0
+output = 0
+
+[limit]
+context = 262_144
+output = 32_768
+
+[modalities]
+input = ["text"]
+output = ["text"]

providers/rapid-mlx/provider.toml

@@ -0,0 +1,5 @@
+name = "Rapid-MLX"
+env = ["RAPID_MLX_API_KEY"]
+npm = "@ai-sdk/openai-compatible"
+api = "http://127.0.0.1:8000/v1"
+doc = "https://github.com/raullenchai/Rapid-MLX"