From 36aec0d086f7321d253cde71b4f3b08f63e35d8f Mon Sep 17 00:00:00 2001
From: rattus <46076784+rattus128@users.noreply.github.com>
Date: Sat, 25 Jul 2026 09:48:52 +1000
Subject: [PATCH] cli_args: bump clamp to 128BGB (#15068)

Some long running chaos testing on a 512GB RAM RTX6000 pro showed that this
is a little bit too low for common template workflows switching around. The
original number was just a guess from me, so go with the scientific result
instead.
---
 comfy/cli_args.py | 2 +-
 main.py           | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/comfy/cli_args.py b/comfy/cli_args.py
index e2e0d97ec..8e03ed032 100644
--- a/comfy/cli_args.py
+++ b/comfy/cli_args.py
@@ -112,7 +112,7 @@ parser.add_argument("--preview-method", type=LatentPreviewMethod, default=Latent
 parser.add_argument("--preview-size", type=int, default=512, help="Sets the maximum preview size for sampler nodes.")
 
 cache_group = parser.add_mutually_exclusive_group()
-cache_group.add_argument("--cache-ram", nargs='*', type=float, default=[], metavar="GB", help="Use RAM pressure caching with the specified headroom thresholds. This is the default caching mode. The first value sets the active-cache threshold; the optional second value sets the inactive-cache/pin threshold. Defaults when no values are provided: active 10%% of system RAM (min 2GB, max 10GB), inactive 100%% of system RAM (max 96GB).")
+cache_group.add_argument("--cache-ram", nargs='*', type=float, default=[], metavar="GB", help="Use RAM pressure caching with the specified headroom thresholds. This is the default caching mode. The first value sets the active-cache threshold; the optional second value sets the inactive-cache/pin threshold. Defaults when no values are provided: active 10%% of system RAM (min 2GB, max 10GB), inactive 100%% of system RAM (max 128GB).")
 cache_group.add_argument("--cache-classic", action="store_true", help="Use the old style (aggressive) caching.")
 cache_group.add_argument("--cache-lru", type=int, default=0, help="Use LRU caching with a maximum of N node results cached. May use more RAM/VRAM.")
 cache_group.add_argument("--cache-none", action="store_true", help="Reduced RAM/VRAM usage at the expense of executing every node for each run.")
diff --git a/main.py b/main.py
index 580074b19..1f16a7f89 100644
--- a/main.py
+++ b/main.py
@@ -319,7 +319,7 @@ def prompt_worker(q, server_instance):
     cache_ram_inactive = 0
     if not args.cache_classic and not args.cache_none and args.cache_lru <= 0:
         cache_ram = min(10.0, max(2.0, comfy.model_management.total_ram * 0.10 / 1024.0))
-        cache_ram_inactive = min(96.0, comfy.model_management.total_ram / 1024.0)
+        cache_ram_inactive = min(128.0, comfy.model_management.total_ram / 1024.0)
         if len(args.cache_ram) > 0:
             cache_ram = args.cache_ram[0]
         if len(args.cache_ram) > 1: