{
 "id": "mimo-v2.6-pro",
 "name": "MiMo-V2.6 Pro",
 "repo": "XiaomiMiMo/MiMo-V2.6-Pro-RL",
 "lab": {
  "name": "Xiaomi",
  "country": "China"
 },
 "released": "2026-09-21",
 "parameters": 1024.22,
 "activeParameters": 42,
 "maxContext": 1048576,
 "architecture": "MoE 384 experts · 10 global-attention layers + 60 sliding-window layers (128 tokens), GQA 8 KV heads (keys 192, values 128)",
 "page": "https://studiotvai.com/vram-requirements/mimo-v2-6-pro",
 "calculator": "https://studiotvai.com/llm-vram-calculator?model=mimo-v2.6-pro",
 "weightsGiB": {
  "native": 524.88,
  "bf16": 1904.15,
  "fp8": 953.82,
  "q4_k_m": 574.44
 },
 "kvCacheGiBPerRequest": [
  {
   "context": 8192,
   "bf16": 0.427,
   "fp8": 0.214
  },
  {
   "context": 32768,
   "bf16": 1.599,
   "fp8": 0.8
  },
  {
   "context": 131072,
   "bf16": 6.287,
   "fp8": 3.143
  },
  {
   "context": 1048576,
   "bf16": 50.037,
   "fp8": 25.018
  }
 ],
 "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": 32,
     "bf16": 96,
     "fp8": 48,
     "q4_k_m": 32
    }
   },
   {
    "gpu": "rtx-5090",
    "name": "GeForce RTX 5090",
    "memoryGB": 32,
    "engine": "llama.cpp",
    "byFormat": {
     "native": 24,
     "bf16": 96,
     "fp8": 48,
     "q4_k_m": 24
    }
   },
   {
    "gpu": "rtx-pro-6000",
    "name": "RTX PRO 6000 Blackwell",
    "memoryGB": 96,
    "engine": "llama.cpp",
    "byFormat": {
     "native": 6,
     "bf16": 24,
     "fp8": 16,
     "q4_k_m": 7
    }
   },
   {
    "gpu": "mac-m5-max-128",
    "name": "Mac M5 Max 128 GB",
    "memoryGB": 96,
    "engine": "llama.cpp",
    "byFormat": {
     "native": 6,
     "bf16": 24,
     "fp8": 16,
     "q4_k_m": 7
    }
   },
   {
    "gpu": "h100",
    "name": "NVIDIA H100",
    "memoryGB": 80,
    "engine": "vLLM",
    "byFormat": {
     "native": 8,
     "bf16": 32,
     "fp8": 16,
     "q4_k_m": 16
    }
   },
   {
    "gpu": "h200",
    "name": "NVIDIA H200",
    "memoryGB": 141,
    "engine": "vLLM",
    "byFormat": {
     "native": 5,
     "bf16": 16,
     "fp8": 8,
     "q4_k_m": 5
    }
   },
   {
    "gpu": "b200",
    "name": "NVIDIA B200 (HGX)",
    "memoryGB": 180,
    "engine": "vLLM",
    "byFormat": {
     "native": 4,
     "bf16": 16,
     "fp8": 7,
     "q4_k_m": 4
    }
   }
  ]
 },
 "ggufFiles": {
  "repo": "ggml-org/MiMo-V2.6-Pro-RL-GGUF",
  "gib": {
   "MXFP4": 516.15,
   "Q2_K": 390.01
  }
 },
 "runsWith": [
  "vLLM",
  "SGLang",
  "llama.cpp (Ollama, LM Studio)",
  "MLX (Mac)"
 ],
 "verified": null,
 "updated": "2026-10-10T15:05:26.095Z"
}