diff --git a/tests/studio/run_real_mlx_smoke.py b/tests/studio/run_real_mlx_smoke.py
index 959ab39577..950eb6f1b1 100644
--- a/tests/studio/run_real_mlx_smoke.py
+++ b/tests/studio/run_real_mlx_smoke.py
@@ -278,6 +278,16 @@ def cmd_train(args) -> int:
             optim = "adamw",
             weight_decay = 0.0,
             max_grad_norm = 1.0,
+            # Explicitly disable the new per-element clip introduced in
+            # #5340 (default max_grad_value=5.0). When both are set the
+            # MLX trainer silently drops max_grad_norm in favour of the
+            # per-element clip, but +-5.0 is far too loose for this
+            # 270M LoRA setup -- losses diverge after step 4 and the
+            # model never memorises "Unsloth!" (verified via the CUDA
+            # mirror at scripts/cuda_mlx_mirror_sim.py). Pinning
+            # max_grad_value=0 makes the smoke depend on the same
+            # max_grad_norm=1.0 the test was originally written for.
+            max_grad_value = 0.0,
             logging_steps = 1,
             max_seq_length = 64,
             seed = SEED,