From f8d8bd6556d0a8ac61cac74d36b9147dc70ffb3d Mon Sep 17 00:00:00 2001
From: Claude <developers@lethean.io>
Date: Mon, 16 Feb 2026 02:01:52 +0000
Subject: [PATCH] feat: use native MLX backend when --model-path is set on
 Apple Silicon

Build-tagged backend selection: MLX on darwin/arm64/mlx, HTTP elsewhere.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---
 internal/cmd/ml/cmd_serve.go             |  9 ++++++---
 internal/cmd/ml/serve_backend_default.go |  9 +++++++++
 internal/cmd/ml/serve_backend_mlx.go     | 22 ++++++++++++++++++++++
 3 files changed, 37 insertions(+), 3 deletions(-)
 create mode 100644 internal/cmd/ml/serve_backend_default.go
 create mode 100644 internal/cmd/ml/serve_backend_mlx.go

diff --git a/internal/cmd/ml/cmd_serve.go b/internal/cmd/ml/cmd_serve.go
index 740eba7..9547f60 100644
--- a/internal/cmd/ml/cmd_serve.go
+++ b/internal/cmd/ml/cmd_serve.go
@@ -79,9 +79,12 @@ type usageInfo struct {
 }
 
 func runServe(cmd *cli.Command, args []string) error {
-	// Create a backend — use HTTP backend pointing to configured API URL.
-	// On macOS with MLX build tag, this will use the native MLX backend instead.
-	backend := ml.NewHTTPBackend(apiURL, modelName)
+	// Try native MLX backend first (macOS arm64 with mlx tag + model-path set),
+	// fall back to HTTP proxy backend.
+	backend, err := createServeBackend()
+	if err != nil {
+		return err
+	}
 
 	mux := http.NewServeMux()
 
diff --git a/internal/cmd/ml/serve_backend_default.go b/internal/cmd/ml/serve_backend_default.go
new file mode 100644
index 0000000..69a1d94
--- /dev/null
+++ b/internal/cmd/ml/serve_backend_default.go
@@ -0,0 +1,9 @@
+//go:build !(darwin && arm64 && mlx)
+
+package ml
+
+import "forge.lthn.ai/core/cli/pkg/ml"
+
+func createServeBackend() (ml.Backend, error) {
+	return ml.NewHTTPBackend(apiURL, modelName), nil
+}
diff --git a/internal/cmd/ml/serve_backend_mlx.go b/internal/cmd/ml/serve_backend_mlx.go
new file mode 100644
index 0000000..f48d1aa
--- /dev/null
+++ b/internal/cmd/ml/serve_backend_mlx.go
@@ -0,0 +1,22 @@
+//go:build darwin && arm64 && mlx
+
+package ml
+
+import (
+	"fmt"
+	"log/slog"
+
+	"forge.lthn.ai/core/cli/pkg/ml"
+)
+
+func createServeBackend() (ml.Backend, error) {
+	if serveModelPath != "" {
+		slog.Info("ml serve: loading native MLX backend", "path", serveModelPath)
+		b, err := ml.NewMLXBackend(serveModelPath)
+		if err != nil {
+			return nil, fmt.Errorf("mlx backend: %w", err)
+		}
+		return b, nil
+	}
+	return ml.NewHTTPBackend(apiURL, modelName), nil
+}