{
 "id": "mage-vl-cowork",
 "name": "Mage-VL-Cowork",
 "repo": "microsoft/Mage-VL-Cowork",
 "lab": {
  "name": "Microsoft",
  "country": "United States"
 },
 "released": "2026-10-30",
 "parameters": 4.741793792,
 "activeParameters": null,
 "maxContext": 262144,
 "architecture": "36 layers · 36 full attention (8 KV × 128)",
 "page": "https://studiotvai.com/vram-requirements/mage-vl-cowork",
 "calculator": "https://studiotvai.com/llm-vram-calculator?model=mage-vl-cowork",
 "weightsGiB": {
  "bf16": 8.83,
  "fp8": 5.14,
  "q4_k_m": 2.56
 },
 "kvCacheGiBPerRequest": [
  {
   "context": 8192,
   "bf16": 1.125,
   "fp8": 0.563
  },
  {
   "context": 32768,
   "bf16": 4.5,
   "fp8": 2.25
  },
  {
   "context": 131072,
   "bf16": 18,
   "fp8": 9
  },
  {
   "context": 262144,
   "bf16": 36,
   "fp8": 18
  }
 ],
 "recurrentStateGiBPerRequest": 0,
 "gpusNeeded": {
  "scenario": "one request of 8192 tokens, BF16 KV cache; vLLM on data-center GPUs, llama.cpp elsewhere",
  "gpus": [
   {
    "gpu": "rtx-4090",
    "name": "GeForce RTX 4090",
    "memoryGB": 24,
    "engine": "llama.cpp",
    "byFormat": {
     "bf16": 1,
     "fp8": 1,
     "q4_k_m": 1
    }
   },
   {
    "gpu": "rtx-5090",
    "name": "GeForce RTX 5090",
    "memoryGB": 32,
    "engine": "llama.cpp",
    "byFormat": {
     "bf16": 1,
     "fp8": 1,
     "q4_k_m": 1
    }
   },
   {
    "gpu": "rtx-pro-6000",
    "name": "RTX PRO 6000 Blackwell",
    "memoryGB": 96,
    "engine": "llama.cpp",
    "byFormat": {
     "bf16": 1,
     "fp8": 1,
     "q4_k_m": 1
    }
   },
   {
    "gpu": "mac-m5-max-128",
    "name": "Mac M5 Max 128 GB",
    "memoryGB": 96,
    "engine": "llama.cpp",
    "byFormat": {
     "bf16": 1,
     "fp8": 1,
     "q4_k_m": 1
    }
   },
   {
    "gpu": "strix-halo",
    "name": "Ryzen AI Max+ 395 128 GB",
    "memoryGB": 96,
    "engine": "llama.cpp",
    "byFormat": {
     "bf16": 1,
     "fp8": 1,
     "q4_k_m": 1
    }
   },
   {
    "gpu": "dgx-spark",
    "name": "DGX Spark (GB10)",
    "memoryGB": 128,
    "engine": "llama.cpp",
    "byFormat": {
     "bf16": 1,
     "fp8": 1,
     "q4_k_m": 1
    }
   },
   {
    "gpu": "h100",
    "name": "NVIDIA H100",
    "memoryGB": 80,
    "engine": "vLLM",
    "byFormat": {
     "bf16": 1,
     "fp8": 1,
     "q4_k_m": 1
    }
   },
   {
    "gpu": "h200",
    "name": "NVIDIA H200",
    "memoryGB": 141,
    "engine": "vLLM",
    "byFormat": {
     "bf16": 1,
     "fp8": 1,
     "q4_k_m": 1
    }
   },
   {
    "gpu": "b200",
    "name": "NVIDIA B200 (HGX)",
    "memoryGB": 180,
    "engine": "vLLM",
    "byFormat": {
     "bf16": 1,
     "fp8": 1,
     "q4_k_m": 1
    }
   }
  ]
 },
 "ggufFiles": {
  "repo": "Hansda/Mage-VL-Cowork-GGUF",
  "gib": {
   "Q2_K": 1.67,
   "Q3_K_M": 2.09,
   "Q4_K_M": 2.53,
   "Q6_K": 3.38,
   "Q8_0": 4.37
  }
 },
 "runsWith": [
  "MLX (Mac)"
 ],
 "verified": {
  "gguf": {
   "day": "2026-11-03",
   "repo": "Hansda/Mage-VL-Cowork-GGUF",
   "kv": "match",
   "ours": 147456,
   "theirs": 147456
  }
 },
 "updated": "2026-11-03T13:04:05.817Z"
}