{
 "id": "minimax-m2.7",
 "name": "MiniMax M2.7",
 "repo": "MiniMaxAI/MiniMax-M2.7",
 "lab": {
  "name": "MiniMax",
  "country": "China"
 },
 "released": "2026-04-09",
 "parameters": 228.69,
 "activeParameters": 10,
 "maxContext": 204800,
 "architecture": "MoE 256 experts · 62 layers, full attention (GQA, 8 KV × 128)",
 "page": "https://studiotvai.com/vram-requirements/minimax-m2-7",
 "calculator": "https://studiotvai.com/llm-vram-calculator?model=minimax-m2.7",
 "weightsGiB": {
  "native": 214.33,
  "bf16": 425.97,
  "fp8": 214.13,
  "q4_k_m": 128.71
 },
 "kvCacheGiBPerRequest": [
  {
   "context": 8192,
   "bf16": 1.938,
   "fp8": 0.969
  },
  {
   "context": 32768,
   "bf16": 7.75,
   "fp8": 3.875
  },
  {
   "context": 131072,
   "bf16": 31,
   "fp8": 15.5
  },
  {
   "context": 204800,
   "bf16": 48.438,
   "fp8": 24.219
  }
 ],
 "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": {
     "native": 16,
     "bf16": 24,
     "fp8": 16,
     "q4_k_m": 7
    }
   },
   {
    "gpu": "rtx-5090",
    "name": "GeForce RTX 5090",
    "memoryGB": 32,
    "engine": "llama.cpp",
    "byFormat": {
     "native": 8,
     "bf16": 16,
     "fp8": 8,
     "q4_k_m": 5
    }
   },
   {
    "gpu": "rtx-pro-6000",
    "name": "RTX PRO 6000 Blackwell",
    "memoryGB": 96,
    "engine": "llama.cpp",
    "byFormat": {
     "native": 3,
     "bf16": 5,
     "fp8": 3,
     "q4_k_m": 2
    }
   },
   {
    "gpu": "mac-m5-max-128",
    "name": "Mac M5 Max 128 GB",
    "memoryGB": 96,
    "engine": "llama.cpp",
    "byFormat": {
     "native": 3,
     "bf16": 5,
     "fp8": 3,
     "q4_k_m": 2
    }
   },
   {
    "gpu": "h100",
    "name": "NVIDIA H100",
    "memoryGB": 80,
    "engine": "vLLM",
    "byFormat": {
     "native": 4,
     "bf16": 7,
     "fp8": 4,
     "q4_k_m": 2
    }
   },
   {
    "gpu": "h200",
    "name": "NVIDIA H200",
    "memoryGB": 141,
    "engine": "vLLM",
    "byFormat": {
     "native": 2,
     "bf16": 4,
     "fp8": 2,
     "q4_k_m": 2
    }
   },
   {
    "gpu": "b200",
    "name": "NVIDIA B200 (HGX)",
    "memoryGB": 180,
    "engine": "vLLM",
    "byFormat": {
     "native": 2,
     "bf16": 3,
     "fp8": 2,
     "q4_k_m": 1
    }
   }
  ]
 },
 "ggufFiles": {
  "repo": "bartowski/MiniMaxAI_MiniMax-M2.7-GGUF",
  "gib": {
   "IQ1_M": 48.62,
   "IQ1_S": 43.47,
   "IQ2_M": 71.17,
   "IQ2_S": 64.38,
   "IQ2_XS": 63.21,
   "IQ2_XXS": 56.67,
   "IQ3_M": 101.33,
   "IQ3_XS": 96.98,
   "IQ3_XXS": 88.65,
   "IQ4_NL": 120.57,
   "IQ4_XS": 114,
   "Q2_K": 74.55,
   "Q2_K_L": 75.11,
   "Q3_K_L": 101.05,
   "Q3_K_M": 96.98,
   "Q3_K_S": 92.49,
   "Q3_K_XL": 101.55,
   "Q4_0": 120.93,
   "Q4_1": 133.65,
   "Q4_K_L": 129.7,
   "Q4_K_M": 129.27,
   "Q4_K_S": 124.65,
   "Q5_K_M": 151.5,
   "Q5_K_S": 146.87,
   "Q6_K": 183.52,
   "Q8_0": 226.44
  }
 },
 "runsWith": [
  "vLLM",
  "SGLang",
  "llama.cpp (Ollama, LM Studio)",
  "MLX (Mac)"
 ],
 "verified": {
  "gguf": {
   "day": "2026-10-10",
   "repo": "bartowski/MiniMaxAI_MiniMax-M2.7-GGUF",
   "kv": "match",
   "ours": 253952,
   "theirs": 253952
  }
 },
 "updated": "2026-10-10T15:05:26.095Z"
}