diff --git a/docs/multimodal.qmd b/docs/multimodal.qmd
index 1c4e28ea7..e63a553b2 100644
--- a/docs/multimodal.qmd
+++ b/docs/multimodal.qmd
@@ -124,6 +124,8 @@ Please make sure to install audio lib via `pip3 install librosa==0.11.0 'mistral
 
 ```yaml
 base_model: mistralai/Voxtral-Mini-3B-2507
+
+processor_type: VoxtralProcessor
 ```
 
 ### Gemma-3 {#sec-gemma-3}
diff --git a/examples/voxtral/voxtral-mini-audio-qlora.yml b/examples/voxtral/voxtral-mini-audio-qlora.yml
index 8fe6adbff..59150c4ca 100644
--- a/examples/voxtral/voxtral-mini-audio-qlora.yml
+++ b/examples/voxtral/voxtral-mini-audio-qlora.yml
@@ -1,5 +1,5 @@
 base_model: mistralai/Voxtral-Mini-3B-2507
-processor_type: AutoProcessor
+processor_type: VoxtralProcessor
 
 # Automatically upload checkpoint and final model to HF
 # hub_model_id: username/custom_model_name
diff --git a/src/axolotl/loaders/processor.py b/src/axolotl/loaders/processor.py
index 7580b2008..b35ea00fd 100644
--- a/src/axolotl/loaders/processor.py
+++ b/src/axolotl/loaders/processor.py
@@ -1,7 +1,5 @@
 """Processor loading functionality for multi-modal models"""
 
-from typing import Any
-
 import transformers
 from transformers import (
     AutoProcessor,
@@ -15,13 +13,33 @@ LOG = get_logger(__name__)
 
 
 def load_processor(cfg: DictDefault, tokenizer: PreTrainedTokenizerBase):
-    processor_kwargs: dict[str, Any] = {}  # Do we actually need this?
-
     processor_cls = AutoProcessor
     if cfg.processor_type:
         processor_cls = getattr(transformers, cfg.processor_type)
 
     if cfg.tokenizer_use_mistral_common:
+
+        def _patch_mistralcommontokenizer():
+            """
+            Transformers v5 stops reading the sub-processor.
+
+            We need to patch this, so both processors use this.
+            """
+            import transformers.tokenization_mistral_common as tokenization_mistral_common
+
+            from axolotl.utils.mistral import HFMistralTokenizer
+
+            tokenization_mistral_common.MistralCommonTokenizer = HFMistralTokenizer
+
+        _patch_mistralcommontokenizer()
+
+        from transformers import VoxtralProcessor
+
+        if processor_cls == VoxtralProcessor:
+            return VoxtralProcessor.from_pretrained(
+                cfg.processor_config,
+            )
+
         from axolotl.utils.mistral import Mistral3Processor
 
         return Mistral3Processor(
@@ -32,7 +50,6 @@ def load_processor(cfg: DictDefault, tokenizer: PreTrainedTokenizerBase):
         cfg.processor_config,
         trust_remote_code=cfg.trust_remote_code or False,
         tokenizer=tokenizer,
-        **processor_kwargs,
     )
 
     # Attempt to load image size from processor if available
diff --git a/src/axolotl/utils/mistral/mistral3_processor.py b/src/axolotl/utils/mistral/mistral3_processor.py
index 85479ca7b..01e8f9f10 100644
--- a/src/axolotl/utils/mistral/mistral3_processor.py
+++ b/src/axolotl/utils/mistral/mistral3_processor.py
@@ -30,6 +30,7 @@ class Mistral3Processor(ProcessorMixin):
     Wraps HFMistralTokenizer and adds image processing capabilities.
     """
 
+    # TODO(nano): This should be removed in transformers V5
     attributes = ["tokenizer"]
     tokenizer_class = "HFMistralTokenizer"