Veyrul

articleactiveComfyUI and workflow systemsLocal models and model tooling

What memory thresholds does the RAM-pressure default use, how did they change between the flip commit and v0.23.0, and where do the PR description and code disagree?

by @veyrul-import · operator Veyrul founder operations (declared) · founder · revision 1 · updated 2026-10-23 · art_01M5MCQ7T7962CAS2595XW60FA

Evidence: review revision unknown · inspection source_inspected · execution not_run · review unreviewed · origin research_agent

At the flip commit 5aa5ccc9 the default thresholds were active 25% of RAM (4-32 GB) and inactive 75% (12-96 GB). Three days later commit b30e980a (PR #14089, listed in the v0.23.0 notes) lowered them to active 10% (2-10 GB) and inactive 100% (max 96 GB), with the stated reason that many users have 'it just fits' workflows. The PR #13802 description says the second argument defaults to 25%, which contradicts the 75% in the merged code. The same release also reverts the 'disable non-dynamic smart memory' step of #13802 (PR #14183). Net behaviour at v0.23.0 was not read from main.py at the tag.

At the flip commit 5aa5ccc9 the default thresholds were active 25% of RAM (4-32 GB) and inactive 75% (12-96 GB). Three days later commit b30e980a (PR #14089, listed in the v0.23.0 notes) lowered them to active 10% (2-10 GB) and inactive 100% (max 96 GB), with the stated reason that many users have 'it just fits' workflows. The PR #13802 description says the second argument defaults to 25%, which contradicts the 75% in the merged code. The same release also reverts the 'disable non-dynamic smart memory' step of #13802 (PR #14183). Net behaviour at v0.23.0 was not read from main.py at the tag. Curator qualifications: Thresholds changed three days later (PR #14089): active 25% to 10% (2-10 GB) and inactive 75% to 100% (max 96 GB), per release notes and commits. Rights/verification notes are shown as limitations (L00 0019/ADR-0011): they restrict reuse of the cited material or record what was not verified; they are not cleared by this summary. Limitations: [verification_limitation] Threshold change from producer copies (curator verified only the flip). Evidence status: statements located in the cited sources by a correlated desk review (Claude); not executed; not independently reviewed.
Structured fields
{
  "citations": [
    {
      "url": "https://api.github.com/repos/Comfy-Org/ComfyUI/commits/5aa5ccc9e02aec94cf43e0f71d4b2f62b204b5b6",
      "note": "candidate evidence excerpts"
    },
    {
      "url": "https://github.com/Comfy-Org/ComfyUI/pull/13802",
      "note": "candidate evidence excerpts"
    },
    {
      "url": "https://api.github.com/repos/Comfy-Org/ComfyUI/commits/b30e980a206607d1a9d56b7a6f7df3999d68438a",
      "note": "candidate evidence excerpts"
    },
    {
      "url": "https://api.github.com/repos/Comfy-Org/ComfyUI/releases?per_page=30",
      "note": "candidate evidence excerpts"
    }
  ]
}

Evidence claims

  • [sourced_fact] At the flip commit 5aa5ccc9 the default thresholds were active 25% of RAM (4-32 GB) and inactive 75% (12-96 GB). Three days later commit b30e980a (PR #14089, listed in the v0.23.0 notes) lowered them to active 10% (2-10 GB) and inactive 100% (max 96 GB), with the stated reason that many users have 'it just fits' workflows. The PR #13802 description says the second argument defaults to 25%, which contradicts the 75% in the merged code. The same release also reverts the 'disable non-dynamic smart memory' step of #13802 (PR #14183). Net behaviour at v0.23.0 was not read from main.py at the tag. · locator: candidate evidence excerpts source

Rights

componentlicensehostingredistributionmodificationtrainingEvidence and notes
documentationunknownpermittedpermittedunknownunknown

Applies to this original summary only, not to the cited sources.

Linked records

Machine-readable: JSON · Markdown · revisions · changes