{
 "license": "CC BY 4.0",
 "attribution": "RigCheck, https://localrigcheck.com",
 "licenseUrl": "https://creativecommons.org/licenses/by/4.0/",
 "name": "FLUX 3 Image Klein",
 "page": "https://localrigcheck.com/flux-3-image-klein/",
 "checker": "https://localrigcheck.com/flux-3-image-klein/#checker",
 "updated": "2026-10-19",
 "sourcesChecked": "2026-10-17",
 "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": [
  "flux"
 ],
 "quickSetup": "Black Forest Labs' int8 ComfyUI route on the card",
 "answerKinds": [
  "published route match"
 ],
 "sizes": [
  {
   "id": "flux-3-image-klein",
   "label": "FLUX 3 Image Klein"
  }
 ],
 "setups": [
  {
   "id": "rtx3060_12",
   "label": "GeForce RTX 3060 (12 GB) + 32 GB RAM",
   "memGB": 12,
   "ramGB": 32,
   "unified": false,
   "quickSetup": "Black Forest Labs' int8 ComfyUI route on the card"
  },
  {
   "id": "rtx4060ti16",
   "label": "GeForce RTX 4060 Ti (16 GB) + 32 GB RAM",
   "memGB": 16,
   "ramGB": 32,
   "unified": false,
   "quickSetup": "Black Forest Labs' int8 ComfyUI route on the card"
  },
  {
   "id": "rtx3090",
   "label": "GeForce RTX 3090 / 3090 Ti (24 GB) + 64 GB RAM",
   "memGB": 24,
   "ramGB": 64,
   "unified": false,
   "quickSetup": "Black Forest Labs' int8 ComfyUI route on the card"
  },
  {
   "id": "rtx5090",
   "label": "GeForce RTX 5090 (32 GB) + 64 GB RAM",
   "memGB": 32,
   "ramGB": 64,
   "unified": false,
   "quickSetup": "Black Forest Labs' int8 ComfyUI route on the card"
  },
  {
   "id": "mac64",
   "label": "Apple Silicon Mac (64 GB unified)",
   "memGB": 64,
   "ramGB": null,
   "unified": true,
   "quickSetup": "Black Forest Labs' int8 ComfyUI route on the card"
  },
  {
   "id": "m5max128",
   "label": "Mac with M5 Max, 40-core GPU (128 GB unified)",
   "memGB": 128,
   "ramGB": null,
   "unified": true,
   "quickSetup": "Black Forest Labs' int8 ComfyUI route on the card"
  },
  {
   "id": "mac256",
   "label": "Mac Studio M3 Ultra (256 GB unified)",
   "memGB": 256,
   "ramGB": null,
   "unified": true,
   "quickSetup": "Black Forest Labs' int8 ComfyUI route on the card"
  },
  {
   "id": "mac512",
   "label": "Mac Studio M3 Ultra (512 GB unified)",
   "memGB": 512,
   "ramGB": null,
   "unified": true,
   "quickSetup": "Black Forest Labs' int8 ComfyUI route on the card"
  }
 ],
 "answers": [
  {
   "setup": "rtx3060_12",
   "size": "flux-3-image-klein",
   "tier": "caveats",
   "answerKind": "published route match",
   "answer": "Matches BFL's 8 GB guidance: the int8 files in ComfyUI",
   "pick": null,
   "where": null,
   "conditions": "BFL: the int8 ComfyUI files run on 8 GB GPUs such as the RTX 3070. Image model, int8 text encoder and VAE together are 11.0 GB; by our reading, on a card smaller than that ComfyUI keeps them on the GPU one at a time and needs system RAM for the rest. BFL gives no RAM figure. The prompt upsampler BFL says not to skip is a 9B model (6.72 GB w4a8, 9.75 GB int8 or 18.8 GB BF16 in ComfyUI); BFL does not say whether its 8 GB figure includes it. When it does not fit with the image model, run it on its own first (BFL's README) or switch it off in the ComfyUI template, with weaker results.",
   "macLimit": false
  },
  {
   "setup": "rtx4060ti16",
   "size": "flux-3-image-klein",
   "tier": "caveats",
   "answerKind": "published route match",
   "answer": "Matches BFL's 8 GB guidance: the int8 files in ComfyUI",
   "pick": null,
   "where": null,
   "conditions": "BFL: the int8 ComfyUI files run on 8 GB GPUs such as the RTX 3070. Image model, int8 text encoder and VAE together are 11.0 GB; by our reading, on a card smaller than that ComfyUI keeps them on the GPU one at a time and needs system RAM for the rest. BFL gives no RAM figure. The prompt upsampler BFL says not to skip is a 9B model (6.72 GB w4a8, 9.75 GB int8 or 18.8 GB BF16 in ComfyUI); BFL does not say whether its 8 GB figure includes it. When it does not fit with the image model, run it on its own first (BFL's README) or switch it off in the ComfyUI template, with weaker results.",
   "macLimit": false
  },
  {
   "setup": "rtx3090",
   "size": "flux-3-image-klein",
   "tier": "caveats",
   "answerKind": "published route match",
   "answer": "Matches BFL's 8 GB guidance: the int8 files in ComfyUI",
   "pick": null,
   "where": null,
   "conditions": "BFL: the int8 ComfyUI files run on 8 GB GPUs such as the RTX 3070. Image model, int8 text encoder and VAE together are 11.0 GB; by our reading, on a card smaller than that ComfyUI keeps them on the GPU one at a time and needs system RAM for the rest. BFL gives no RAM figure. The prompt upsampler BFL says not to skip is a 9B model (6.72 GB w4a8, 9.75 GB int8 or 18.8 GB BF16 in ComfyUI); BFL does not say whether its 8 GB figure includes it. When it does not fit with the image model, run it on its own first (BFL's README) or switch it off in the ComfyUI template, with weaker results.",
   "macLimit": false
  },
  {
   "setup": "rtx5090",
   "size": "flux-3-image-klein",
   "tier": "caveats",
   "answerKind": "published route match",
   "answer": "Matches BFL's 8 GB guidance: the int8 files in ComfyUI",
   "pick": null,
   "where": null,
   "conditions": "BFL: the int8 ComfyUI files run on 8 GB GPUs such as the RTX 3070. Image model, int8 text encoder and VAE together are 11.0 GB; by our reading, on a card smaller than that ComfyUI keeps them on the GPU one at a time and needs system RAM for the rest. BFL gives no RAM figure. The prompt upsampler BFL says not to skip is a 9B model (6.72 GB w4a8, 9.75 GB int8 or 18.8 GB BF16 in ComfyUI); BFL does not say whether its 8 GB figure includes it. When it does not fit with the image model, run it on its own first (BFL's README) or switch it off in the ComfyUI template, with weaker results. NVIDIA measured about 4 seconds per 1 MP image on an RTX 5090 (distilled, int8, 16 steps, ComfyUI, upsampler not included).",
   "macLimit": false
  },
  {
   "setup": "mac64",
   "size": "flux-3-image-klein",
   "tier": "na",
   "answerKind": "published route match",
   "answer": "unknown",
   "pick": null,
   "where": null,
   "conditions": "No published FLUX 3 Klein route for this hardware. Black Forest Labs and NVIDIA publish no Apple silicon figures, and BFL's reference code installs for CUDA. A community MLX conversion for mflux exists; we have not verified it. The prompt upsampler BFL says not to skip is a 9B model (6.72 GB w4a8, 9.75 GB int8 or 18.8 GB BF16 in ComfyUI); BFL does not say whether its 8 GB figure includes it. When it does not fit with the image model, run it on its own first (BFL's README) or switch it off in the ComfyUI template, with weaker results.",
   "macLimit": false
  },
  {
   "setup": "m5max128",
   "size": "flux-3-image-klein",
   "tier": "na",
   "answerKind": "published route match",
   "answer": "unknown",
   "pick": null,
   "where": null,
   "conditions": "No published FLUX 3 Klein route for this hardware. Black Forest Labs and NVIDIA publish no Apple silicon figures, and BFL's reference code installs for CUDA. A community MLX conversion for mflux exists; we have not verified it. The prompt upsampler BFL says not to skip is a 9B model (6.72 GB w4a8, 9.75 GB int8 or 18.8 GB BF16 in ComfyUI); BFL does not say whether its 8 GB figure includes it. When it does not fit with the image model, run it on its own first (BFL's README) or switch it off in the ComfyUI template, with weaker results.",
   "macLimit": false
  },
  {
   "setup": "mac256",
   "size": "flux-3-image-klein",
   "tier": "na",
   "answerKind": "published route match",
   "answer": "unknown",
   "pick": null,
   "where": null,
   "conditions": "No published FLUX 3 Klein route checked here for this device.",
   "macLimit": false
  },
  {
   "setup": "mac512",
   "size": "flux-3-image-klein",
   "tier": "na",
   "answerKind": "published route match",
   "answer": "unknown",
   "pick": null,
   "where": null,
   "conditions": "No published FLUX 3 Klein route checked here for this device.",
   "macLimit": false
  }
 ]
}