{
 "license": "CC BY 4.0",
 "attribution": "RigCheck, https://localrigcheck.com",
 "licenseUrl": "https://creativecommons.org/licenses/by/4.0/",
 "name": "Qwen3.8-Flash-Next",
 "page": "https://localrigcheck.com/qwen-3-8-flash-next/",
 "checker": "https://localrigcheck.com/qwen-3-8-flash-next/#checker",
 "updated": "2026-10-19",
 "sourcesChecked": "2026-10-08",
 "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": [
  "qwen"
 ],
 "quickSetup": "graphics cards: llama.cpp on one graphics card, a 32K context, no image input; Macs: llama.cpp in unified memory, a 32K context, no image input",
 "answerKinds": [
  "capacity estimate"
 ],
 "sizes": [
  {
   "id": "qwen-3-8-flash-next",
   "label": "Qwen3.8-Flash-Next"
  }
 ],
 "setups": [
  {
   "id": "rtx3060_12",
   "label": "GeForce RTX 3060 (12 GB) + 32 GB RAM",
   "memGB": 12,
   "ramGB": 32,
   "unified": false,
   "quickSetup": "llama.cpp on one graphics card, a 32K context, no image input"
  },
  {
   "id": "rtx4060ti16",
   "label": "GeForce RTX 4060 Ti (16 GB) + 32 GB RAM",
   "memGB": 16,
   "ramGB": 32,
   "unified": false,
   "quickSetup": "llama.cpp on one graphics card, a 32K context, no image input"
  },
  {
   "id": "rtx3090",
   "label": "GeForce RTX 3090 / 3090 Ti (24 GB) + 64 GB RAM",
   "memGB": 24,
   "ramGB": 64,
   "unified": false,
   "quickSetup": "llama.cpp on one graphics card, a 32K context, no image input"
  },
  {
   "id": "rtx5090",
   "label": "GeForce RTX 5090 (32 GB) + 64 GB RAM",
   "memGB": 32,
   "ramGB": 64,
   "unified": false,
   "quickSetup": "llama.cpp on one graphics card, a 32K context, no image input"
  },
  {
   "id": "mac64",
   "label": "Apple Silicon Mac (64 GB unified)",
   "memGB": 64,
   "ramGB": null,
   "unified": true,
   "quickSetup": "llama.cpp in unified memory, a 32K context, no image input"
  },
  {
   "id": "m5max128",
   "label": "Mac with M5 Max, 40-core GPU (128 GB unified)",
   "memGB": 128,
   "ramGB": null,
   "unified": true,
   "quickSetup": "llama.cpp in unified memory, a 32K context, no image input"
  },
  {
   "id": "mac256",
   "label": "Mac Studio M3 Ultra (256 GB unified)",
   "memGB": 256,
   "ramGB": null,
   "unified": true,
   "quickSetup": "llama.cpp in unified memory, a 32K context, no image input"
  },
  {
   "id": "mac512",
   "label": "Mac Studio M3 Ultra (512 GB unified)",
   "memGB": 512,
   "ramGB": null,
   "unified": true,
   "quickSetup": "llama.cpp in unified memory, a 32K context, no image input"
  }
 ],
 "answers": [
  {
   "setup": "rtx3060_12",
   "size": "qwen-3-8-flash-next",
   "tier": "no",
   "answerKind": "capacity estimate",
   "answer": "does not fit",
   "pick": null,
   "where": null,
   "conditions": "Even the smallest file (UD-IQ1_S, 72.5 GB) needs about 76.1 GB.",
   "macLimit": false
  },
  {
   "setup": "rtx4060ti16",
   "size": "qwen-3-8-flash-next",
   "tier": "no",
   "answerKind": "capacity estimate",
   "answer": "does not fit",
   "pick": null,
   "where": null,
   "conditions": "Even the smallest file (UD-IQ1_S, 72.5 GB) needs about 76.1 GB.",
   "macLimit": false
  },
  {
   "setup": "rtx3090",
   "size": "qwen-3-8-flash-next",
   "tier": "caveats",
   "answerKind": "capacity estimate",
   "answer": "fits with caveats: UD-IQ1_S, GPU and system RAM (54 GB in RAM)",
   "pick": "UD-IQ1_S",
   "where": "GPU and system RAM (54 GB in RAM)",
   "conditions": "Flash-Next uses combined memory totals; per-card layer placement is not modeled. Close fits are uncertain until runtime allocation is checked.",
   "macLimit": false
  },
  {
   "setup": "rtx5090",
   "size": "qwen-3-8-flash-next",
   "tier": "caveats",
   "answerKind": "capacity estimate",
   "answer": "fits with caveats: UD-Q2_K_XL, GPU and system RAM (53.1 GB in RAM)",
   "pick": "UD-Q2_K_XL",
   "where": "GPU and system RAM (53.1 GB in RAM)",
   "conditions": "Flash-Next uses combined memory totals; per-card layer placement is not modeled. Close fits are uncertain until runtime allocation is checked.",
   "macLimit": false
  },
  {
   "setup": "mac64",
   "size": "qwen-3-8-flash-next",
   "tier": "na",
   "answerKind": "capacity estimate",
   "answer": "unknown",
   "pick": null,
   "where": null,
   "conditions": "This checker covers NVIDIA cards and the unified-memory machines in its list.",
   "macLimit": false
  },
  {
   "setup": "m5max128",
   "size": "qwen-3-8-flash-next",
   "tier": "good",
   "answerKind": "capacity estimate",
   "answer": "fits: UD-Q4_K_XL, unified memory (after raising the Mac's GPU wired-memory limit)",
   "pick": "UD-Q4_K_XL",
   "where": "unified memory",
   "conditions": "",
   "macLimit": true
  },
  {
   "setup": "mac256",
   "size": "qwen-3-8-flash-next",
   "tier": "good",
   "answerKind": "capacity estimate",
   "answer": "fits: Q8_0, unified memory (after raising the Mac's GPU wired-memory limit)",
   "pick": "Q8_0",
   "where": "unified memory",
   "conditions": "",
   "macLimit": true
  },
  {
   "setup": "mac512",
   "size": "qwen-3-8-flash-next",
   "tier": "good",
   "answerKind": "capacity estimate",
   "answer": "fits: Q8_0, unified memory (after raising the Mac's GPU wired-memory limit)",
   "pick": "Q8_0",
   "where": "unified memory",
   "conditions": "",
   "macLimit": true
  }
 ]
}