diff --git a/studio/backend/core/inference/llama_cpp.py b/studio/backend/core/inference/llama_cpp.py
index 90e8aeba75..06cf4363e9 100644
--- a/studio/backend/core/inference/llama_cpp.py
+++ b/studio/backend/core/inference/llama_cpp.py
@@ -2909,9 +2909,7 @@ class LlamaCppBackend:
             # (Gemma) grows KV with slots and would otherwise be under-reserved.
             # swa_full: the draft caches against the full target window, so its SWA
             # layers are not window-capped and grow with n_ctx (safe upper bound).
-            kv = db._estimate_kv_cache_bytes(
-                n_ctx, heavier, n_parallel = n_parallel, swa_full = True
-            )
+            kv = db._estimate_kv_cache_bytes(n_ctx, heavier, n_parallel = n_parallel, swa_full = True)
             return kv or None
         nextn = self._nextn_predict_layers or 0
         n_kv = self._n_kv_heads or self._n_heads