diff --git a/invokeai/app/api/routers/model_manager.py b/invokeai/app/api/routers/model_manager.py
index 99f00423c6..1730d383f0 100644
--- a/invokeai/app/api/routers/model_manager.py
+++ b/invokeai/app/api/routers/model_manager.py
@@ -6,6 +6,7 @@ import pathlib
 import shutil
 import traceback
 from copy import deepcopy
+from enum import Enum
 from typing import Any, Dict, List, Optional, Type
 
 from fastapi import Body, Path, Query, Response, UploadFile
@@ -16,6 +17,7 @@ from pydantic import AnyHttpUrl, BaseModel, ConfigDict, Field
 from starlette.exceptions import HTTPException
 from typing_extensions import Annotated
 
+from invokeai.app.services.config import get_config
 from invokeai.app.services.model_images.model_images_common import ModelImageFileNotFoundException
 from invokeai.app.services.model_install.model_install_common import ModelInstallJob
 from invokeai.app.services.model_records import (
@@ -32,6 +34,7 @@ from invokeai.backend.model_manager.config import (
     ModelType,
     SubModelType,
 )
+from invokeai.backend.model_manager.load.model_cache.model_cache_base import CacheStats
 from invokeai.backend.model_manager.metadata.fetch.huggingface import HuggingFaceMetadataFetch
 from invokeai.backend.model_manager.metadata.metadata_base import ModelMetadataWithFiles, UnknownMetadataException
 from invokeai.backend.model_manager.search import ModelSearch
@@ -53,6 +56,13 @@ class ModelsList(BaseModel):
     model_config = ConfigDict(use_enum_values=True)
 
 
+class CacheType(str, Enum):
+    """Cache type - one of vram or ram."""
+
+    RAM = "RAM"
+    VRAM = "VRAM"
+
+
 def add_cover_image_to_model_config(config: AnyModelConfig, dependencies: Type[ApiDependencies]) -> AnyModelConfig:
     """Add a cover image URL to a model configuration."""
     cover_image = dependencies.invoker.services.model_images.get_url(config.key)
@@ -174,18 +184,6 @@ async def get_model_record(
         raise HTTPException(status_code=404, detail=str(e))
 
 
-# @model_manager_router.get("/summary", operation_id="list_model_summary")
-# async def list_model_summary(
-#     page: int = Query(default=0, description="The page to get"),
-#     per_page: int = Query(default=10, description="The number of models per page"),
-#     order_by: ModelRecordOrderBy = Query(default=ModelRecordOrderBy.Default, description="The attribute to order by"),
-# ) -> PaginatedResults[ModelSummary]:
-#     """Gets a page of model summary data."""
-#     record_store = ApiDependencies.invoker.services.model_manager.store
-#     results: PaginatedResults[ModelSummary] = record_store.list_models(page=page, per_page=per_page, order_by=order_by)
-#     return results
-
-
 class FoundModel(BaseModel):
     path: str = Field(description="Path to the model")
     is_installed: bool = Field(description="Whether or not the model is already installed")
@@ -816,3 +814,61 @@ async def get_starter_models() -> list[StarterModel]:
         model.dependencies = missing_deps
 
     return starter_models
+
+
+@model_manager_router.get(
+    "/model_cache",
+    operation_id="get_cache_size",
+    response_model=float,
+    summary="Get maximum size of model manager RAM or VRAM cache.",
+)
+async def get_cache_size(cache_type: CacheType = Query(description="The cache type", default=CacheType.RAM)) -> float:
+    """Return the current RAM or VRAM cache size setting (in GB)."""
+    cache = ApiDependencies.invoker.services.model_manager.load.ram_cache
+    return cache.max_cache_size if cache_type == CacheType.RAM else cache.max_vram_cache_size
+
+
+@model_manager_router.put(
+    "/model_cache",
+    operation_id="set_cache_size",
+    response_model=float,
+    summary="Set maximum size of model manager RAM or VRAM cache, optionally writing new value out to invokeai.yaml config file.",
+)
+async def set_cache_size(
+    value: float = Query(description="The new value for the maximum cache size"),
+    cache_type: CacheType = Query(description="The cache type", default=CacheType.RAM),
+    persist: bool = Query(description="Write new value out to invokeai.yaml", default=False),
+) -> float:
+    """Set the current RAM or VRAM cache size setting (in GB). ."""
+    cache = ApiDependencies.invoker.services.model_manager.load.ram_cache
+    app_config = get_config()
+    if cache_type == CacheType.RAM:
+        cache.max_cache_size = value
+        app_config.ram = value
+    elif cache_type == CacheType.VRAM:
+        cache.max_vram_cache_size = value
+        app_config.vram = value
+
+    if persist:
+        config_path = app_config.config_file_path
+        print(f"DEBUG: config_path = {config_path}")
+        try:
+            shutil.copy(config_path, config_path.with_suffix(".yaml.bak"))
+            app_config.write_file(config_path)
+        except Exception as e:
+            shutil.move(config_path.with_suffix(".yaml.bak"), config_path)
+            raise RuntimeError(f"Failed to write modified configuration to {config_path}: {e}") from e
+
+    return cache.max_vram_cache_size if cache_type == CacheType.VRAM else cache.max_cache_size
+
+
+@model_manager_router.get(
+    "/stats",
+    operation_id="get_stats",
+    response_model=Optional[CacheStats],
+    summary="Get model manager RAM cache performance statistics.",
+)
+async def get_stats() -> Optional[CacheStats]:
+    """Return performance statistics on the model manager's RAM cache. Will return null if no models have been loaded."""
+
+    return ApiDependencies.invoker.services.model_manager.load.ram_cache.stats
diff --git a/invokeai/backend/model_manager/load/load_default.py b/invokeai/backend/model_manager/load/load_default.py
index a63cc66a86..13030395d2 100644
--- a/invokeai/backend/model_manager/load/load_default.py
+++ b/invokeai/backend/model_manager/load/load_default.py
@@ -79,8 +79,10 @@ class ModelLoader(ModelLoaderBase):
     def _convert_and_load(
         self, config: AnyModelConfig, model_path: Path, submodel_type: Optional[SubModelType] = None
     ) -> ModelLockerBase:
+        stats_name = ":".join([config.base, config.type, config.name, (submodel_type or "")])
+
         try:
-            return self._ram_cache.get(config.key, submodel_type)
+            return self._ram_cache.get(config.key, submodel_type, stats_name=stats_name)
         except IndexError:
             pass
 
@@ -100,7 +102,7 @@ class ModelLoader(ModelLoaderBase):
         return self._ram_cache.get(
             key=config.key,
             submodel_type=submodel_type,
-            stats_name=":".join([config.base, config.type, config.name, (submodel_type or "")]),
+            stats_name=stats_name,
         )
 
     def get_size_fs(
diff --git a/invokeai/backend/model_manager/load/model_cache/model_cache_base.py b/invokeai/backend/model_manager/load/model_cache/model_cache_base.py
index 012fd42d55..6d775cb632 100644
--- a/invokeai/backend/model_manager/load/model_cache/model_cache_base.py
+++ b/invokeai/backend/model_manager/load/model_cache/model_cache_base.py
@@ -128,7 +128,24 @@ class ModelCacheBase(ABC, Generic[T]):
     @property
     @abstractmethod
     def max_cache_size(self) -> float:
-        """Return true if the cache is configured to lazily offload models in VRAM."""
+        """Return the maximum size the RAM cache can grow to."""
+        pass
+
+    @max_cache_size.setter
+    @abstractmethod
+    def max_cache_size(self, value: float) -> None:
+        """Set the cap on vram cache size."""
+
+    @property
+    @abstractmethod
+    def max_vram_cache_size(self) -> float:
+        """Return the maximum size the VRAM cache can grow to."""
+        pass
+
+    @max_vram_cache_size.setter
+    @abstractmethod
+    def max_vram_cache_size(self, value: float) -> float:
+        """Set the maximum size the VRAM cache can grow to."""
         pass
 
     @abstractmethod
diff --git a/invokeai/backend/model_manager/load/model_cache/model_cache_default.py b/invokeai/backend/model_manager/load/model_cache/model_cache_default.py
index d48e45426e..173acd6bb1 100644
--- a/invokeai/backend/model_manager/load/model_cache/model_cache_default.py
+++ b/invokeai/backend/model_manager/load/model_cache/model_cache_default.py
@@ -60,9 +60,7 @@ class ModelCache(ModelCacheBase[AnyModel]):
         execution_device: torch.device = torch.device("cuda"),
         storage_device: torch.device = torch.device("cpu"),
         precision: torch.dtype = torch.float16,
-        sequential_offload: bool = False,
         lazy_offloading: bool = True,
-        sha_chunksize: int = 16777216,
         log_memory_usage: bool = False,
         logger: Optional[Logger] = None,
     ):
@@ -74,7 +72,6 @@ class ModelCache(ModelCacheBase[AnyModel]):
         :param storage_device: Torch device to save inactive model in [torch.device('cpu')]
         :param precision: Precision for loaded models [torch.float16]
         :param lazy_offloading: Keep model in VRAM until another model needs to be loaded
-        :param sequential_offload: Conserve VRAM by loading and unloading each stage of the pipeline sequentially
         :param log_memory_usage: If True, a memory snapshot will be captured before and after every model cache
             operation, and the result will be logged (at debug level). There is a time cost to capturing the memory
             snapshots, so it is recommended to disable this feature unless you are actively inspecting the model cache's
@@ -124,6 +121,16 @@ class ModelCache(ModelCacheBase[AnyModel]):
         """Set the cap on cache size."""
         self._max_cache_size = value
 
+    @property
+    def max_vram_cache_size(self) -> float:
+        """Return the cap on vram cache size."""
+        return self._max_vram_cache_size
+
+    @max_vram_cache_size.setter
+    def max_vram_cache_size(self, value: float) -> None:
+        """Set the cap on vram cache size."""
+        self._max_vram_cache_size = value
+
     @property
     def stats(self) -> Optional[CacheStats]:
         """Return collected CacheStats object."""