diff --git a/config_sample.yml b/config_sample.yml
index dc36241..fe723a5 100644
--- a/config_sample.yml
+++ b/config_sample.yml
@@ -45,9 +45,6 @@ model:
   # Disable Flash-attention 2. Set to True for GPUs lower than Nvidia's 3000 series. (default: False)
   no_flash_attention: False
 
-  # Enable low vram optimizations in exllamav2 (default: False)
-  low_mem: False
-
   # Enable 8 bit cache mode for VRAM savings (slight performance hit). Possible values FP16, FP8. (default: FP16)
   cache_mode: FP16
 
diff --git a/model.py b/model.py
index 25bfb25..6d3d8c7 100644
--- a/model.py
+++ b/model.py
@@ -81,8 +81,12 @@ class ModelContainer:
         self.config.scale_alpha_value = kwargs.get("rope_alpha") or self.calculate_rope_alpha(base_seq_len)
 
         if "no_flash_attn" in kwargs: self.config.no_flash_attn = kwargs["no_flash_attn"]
+
+        # low_mem is currently broken in exllamav2. Don't use it until it's fixed.
+        """
         if "low_mem" in kwargs and kwargs["low_mem"]:
             self.config.set_low_mem()
+        """
 
         chunk_size = min(kwargs.get("chunk_size", 2048), self.config.max_seq_len)
         self.config.max_input_len = chunk_size