{
 "license": "CC BY 4.0",
 "attribution": "RigCheck, https://localrigcheck.com",
 "licenseUrl": "https://creativecommons.org/licenses/by/4.0/",
 "name": "Qwen-Image-2.1",
 "page": "https://localrigcheck.com/qwen-image-2-1/",
 "checker": "https://localrigcheck.com/qwen-image-2-1/#checker",
 "updated": "2026-10-19",
 "sourcesChecked": "2026-10-12",
 "note": "The checker's own quick-mode answers on fixed setups, in its own words. answerKind says what kind of answer each is (a RigCheck capacity estimate, a planning budget, a published route or recipe match); none is a measured setup. tier 'na' means unknown, not 'does not fit'. Conditions are part of the answer.",
 "tiers": {
  "good": "an answer without caveats of the checker's own kind; a limit stated in the answer (such as raising a Mac's GPU wired-memory limit, macLimit) still applies",
  "caveats": "an answer with caveats (part in system RAM, a planning estimate, an unverified peak or route)",
  "experimental": "only an experimental path",
  "no": "does not fit, or below the smallest published figure",
  "na": "unknown: the checker covers no route or source for this hardware"
 },
 "checkers": [
  "image"
 ],
 "quickSetup": "graphics cards: base model, INT8, 512×512, batch one, no reference images; Macs: base model, the GGUF files (not INT8), 512×512, batch one, no reference images",
 "answerKinds": [
  "planning budget"
 ],
 "sizes": [
  {
   "id": "qwen-image-2-1",
   "label": "Qwen-Image-2.1 (Base and Turbo)"
  }
 ],
 "setups": [
  {
   "id": "rtx3060_12",
   "label": "GeForce RTX 3060 (12 GB) + 32 GB RAM",
   "memGB": 12,
   "ramGB": 32,
   "unified": false,
   "quickSetup": "base model, INT8, 512×512, batch one, no reference images"
  },
  {
   "id": "rtx4060ti16",
   "label": "GeForce RTX 4060 Ti (16 GB) + 32 GB RAM",
   "memGB": 16,
   "ramGB": 32,
   "unified": false,
   "quickSetup": "base model, INT8, 512×512, batch one, no reference images"
  },
  {
   "id": "rtx3090",
   "label": "GeForce RTX 3090 / 3090 Ti (24 GB) + 64 GB RAM",
   "memGB": 24,
   "ramGB": 64,
   "unified": false,
   "quickSetup": "base model, INT8, 512×512, batch one, no reference images"
  },
  {
   "id": "rtx5090",
   "label": "GeForce RTX 5090 (32 GB) + 64 GB RAM",
   "memGB": 32,
   "ramGB": 64,
   "unified": false,
   "quickSetup": "base model, INT8, 512×512, batch one, no reference images"
  },
  {
   "id": "mac64",
   "label": "Apple Silicon Mac (64 GB unified)",
   "memGB": 64,
   "ramGB": null,
   "unified": true,
   "quickSetup": "base model, the GGUF files (not INT8), 512×512, batch one, no reference images"
  },
  {
   "id": "m5max128",
   "label": "Mac with M5 Max, 40-core GPU (128 GB unified)",
   "memGB": 128,
   "ramGB": null,
   "unified": true,
   "quickSetup": "base model, the GGUF files (not INT8), 512×512, batch one, no reference images"
  },
  {
   "id": "mac256",
   "label": "Mac Studio M3 Ultra (256 GB unified)",
   "memGB": 256,
   "ramGB": null,
   "unified": true,
   "quickSetup": "base model, the GGUF files (not INT8), 512×512, batch one, no reference images"
  },
  {
   "id": "mac512",
   "label": "Mac Studio M3 Ultra (512 GB unified)",
   "memGB": 512,
   "ramGB": null,
   "unified": true,
   "quickSetup": "base model, the GGUF files (not INT8), 512×512, batch one, no reference images"
  }
 ],
 "answers": [
  {
   "setup": "rtx3060_12",
   "size": "qwen-image-2-1",
   "tier": "caveats",
   "answerKind": "planning budget",
   "answer": "Above the all-components-resident planning budget; offload peak unverified",
   "pick": null,
   "where": null,
   "conditions": "Uncalibrated allowances, not a minimum or a guarantee. Full checkpoint files are counted in host RAM even when mmap or sequential loading can use less. Actual peak depends on attention, prefix caches, VAE tiling, reference sizes and backend. No speed prediction.",
   "macLimit": false
  },
  {
   "setup": "rtx4060ti16",
   "size": "qwen-image-2-1",
   "tier": "na",
   "answerKind": "planning budget",
   "answer": "unknown",
   "pick": null,
   "where": null,
   "conditions": "No published route checked here for this device.",
   "macLimit": false
  },
  {
   "setup": "rtx3090",
   "size": "qwen-image-2-1",
   "tier": "caveats",
   "answerKind": "planning budget",
   "answer": "Above the all-components-resident planning budget; offload peak unverified",
   "pick": null,
   "where": null,
   "conditions": "Uncalibrated allowances, not a minimum or a guarantee. Full checkpoint files are counted in host RAM even when mmap or sequential loading can use less. Actual peak depends on attention, prefix caches, VAE tiling, reference sizes and backend. No speed prediction.",
   "macLimit": false
  },
  {
   "setup": "rtx5090",
   "size": "qwen-image-2-1",
   "tier": "caveats",
   "answerKind": "planning budget",
   "answer": "Within the all-components-resident planning budget; allocation unverified",
   "pick": null,
   "where": null,
   "conditions": "Uncalibrated allowances, not a minimum or a guarantee. Full checkpoint files are counted in host RAM even when mmap or sequential loading can use less. Actual peak depends on attention, prefix caches, VAE tiling, reference sizes and backend. No speed prediction.",
   "macLimit": false
  },
  {
   "setup": "mac64",
   "size": "qwen-image-2-1",
   "tier": "caveats",
   "answerKind": "planning budget",
   "answer": "Mac GGUF is within the planning budget; Metal execution unverified here",
   "pick": null,
   "where": null,
   "conditions": "Uncalibrated allowances, not a minimum or a guarantee. Full checkpoint files are counted in host RAM even when mmap or sequential loading can use less. Actual peak depends on attention, prefix caches, VAE tiling, reference sizes and backend. No speed prediction.",
   "macLimit": false
  },
  {
   "setup": "m5max128",
   "size": "qwen-image-2-1",
   "tier": "caveats",
   "answerKind": "planning budget",
   "answer": "Mac GGUF is within the planning budget; Metal execution unverified here",
   "pick": null,
   "where": null,
   "conditions": "Uncalibrated allowances, not a minimum or a guarantee. Full checkpoint files are counted in host RAM even when mmap or sequential loading can use less. Actual peak depends on attention, prefix caches, VAE tiling, reference sizes and backend. No speed prediction.",
   "macLimit": false
  },
  {
   "setup": "mac256",
   "size": "qwen-image-2-1",
   "tier": "caveats",
   "answerKind": "planning budget",
   "answer": "Mac GGUF is within the planning budget; Metal execution unverified here",
   "pick": null,
   "where": null,
   "conditions": "Uncalibrated allowances, not a minimum or a guarantee. Full checkpoint files are counted in host RAM even when mmap or sequential loading can use less. Actual peak depends on attention, prefix caches, VAE tiling, reference sizes and backend. No speed prediction.",
   "macLimit": false
  },
  {
   "setup": "mac512",
   "size": "qwen-image-2-1",
   "tier": "caveats",
   "answerKind": "planning budget",
   "answer": "Mac GGUF is within the planning budget; Metal execution unverified here",
   "pick": null,
   "where": null,
   "conditions": "Uncalibrated allowances, not a minimum or a guarantee. Full checkpoint files are counted in host RAM even when mmap or sequential loading can use less. Actual peak depends on attention, prefix caches, VAE tiling, reference sizes and backend. No speed prediction.",
   "macLimit": false
  }
 ]
}