{
  "$type": "site.standard.document",
  "bskyPostRef": {
    "cid": "bafyreibq53g7pzgnt57r37mr4tymvbumc3mr3ezii75rts2yfydidrkkfa",
    "uri": "at://did:plc:pgryn3ephfd2xgft23qokfzt/app.bsky.feed.post/3mpnbibj3le72"
  },
  "path": "/t/17-zerogpu-slots-reported-but-only-8-spaces-listed/177337#post_1",
  "publishedAt": "2026-07-02T03:55:34.000Z",
  "site": "https://discuss.huggingface.co",
  "textContent": "I was trying to run a Zero GPU space, but I reached a quota error: “Quota exceeded for flavor zero-a10g (requested=1): current=17, limit=10”.\n\n17 zerogpu spaces assigned.\n\n\n\n    api.get_space_runtime(repo_id=\"r3gm/wan2-2-fp8da-aoti-preview-r\")\n\n    SpaceRuntime(stage='PAUSED', hardware=None, requested_hardware='zero-a10g', sleep_time=172800, storage=None, dev_mode=False, hot_reloading=None, volumes=None, raw={'stage': 'PAUSED', 'hardware': {'current': None, 'requested': 'zero-a10g'}, 'gcTimeout': 172800, 'errorMessage': 'Quota exceeded for flavor zero-a10g (requested=1): current=17, limit=10', 'replicas': {'requested': 1}, 'devMode': False, 'domains': [{'domain': 'r3gm-wan2-2-fp8da-aoti-preview-r.hf.space', 'stage': 'READY'}]})\n\n\nHowever, when I verify my spaces that request the zero-a10g hardware, I only see 8 spaces, and 7 of them are running.\n\n\n    ID                                  Stage           Replicas\n\n    r3gm/wan2-2-fp8da-aoti-preview      RUNNING         {'current': 6, 'requested': 'auto'}\n    r3gm/AICoverGen                     RUNNING         {'current': 1, 'requested': 1}\n    r3gm/rvc_zero                       RUNNING         {'current': 1, 'requested': 1}\n    r3gm/Audio_separator                RUNNING         {'current': 1, 'requested': 1}\n    r3gm/DiffuseCraft                   RUNNING         {'current': 1, 'requested': 'auto'}\n    r3gm/upscale_board                  RUNNING         {'current': 1, 'requested': 1}\n    r3gm/wan2-2-fp8da-aoti-old-backup   RUNNING         {'current': 1, 'requested': 1}\n    r3gm/wan2-2-fp8da-aoti-preview-r    PAUSED          {'requested': 1}\n\n\n\n\nThe only explanation I can think of is that replicas are also counted in the Zero GPU slot limit. If two spaces are set to “auto” replicas, their maximum of 6 each would add up to 12, and when combined with the other running spaces, the total becomes 17.",
  "title": "17 ZeroGPU Slots Reported but Only 8 Spaces Listed"
}