{
 "id": "kimi-k2.6",
 "name": "Kimi K2.6",
 "repo": "moonshotai/Kimi-K2.6",
 "lab": {
  "name": "Moonshot AI",
  "country": "China"
 },
 "released": "2026-04-14",
 "parameters": 1026.88,
 "activeParameters": 32,
 "maxContext": 262144,
 "architecture": "MoE 384 experts · MLA (512 + 64 latent) on 61 layers · INT4 checkpoint (group size 32)",
 "page": "https://studiotvai.com/vram-requirements/kimi-k2-6",
 "calculator": "https://studiotvai.com/llm-vram-calculator?model=kimi-k2.6",
 "weightsGiB": {
  "native": 554.3,
  "bf16": 1912.71,
  "fp8": 958.54,
  "q4_k_m": 577.37
 },
 "kvCacheGiBPerRequest": [
  {
   "context": 8192,
   "bf16": 0.536,
   "fp8": 0.268
  },
  {
   "context": 32768,
   "bf16": 2.145,
   "fp8": 1.072
  },
  {
   "context": 131072,
   "bf16": 8.578,
   "fp8": 4.289
  },
  {
   "context": 262144,
   "bf16": 17.156,
   "fp8": 8.578
  }
 ],
 "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": 128,
     "fp8": 64,
     "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": 7,
     "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": 7,
     "bf16": 24,
     "fp8": 16,
     "q4_k_m": 7
    }
   },
   {
    "gpu": "h100",
    "name": "NVIDIA H100",
    "memoryGB": 80,
    "engine": "vLLM",
    "byFormat": {
     "native": 16,
     "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": "DevQuasar/moonshotai.Kimi-K2.6-GGUF",
  "gib": {
   "IQ2_XS": 278.06,
   "Q2_K": 347.25,
   "Q3_K_M": 455.5,
   "Q4_K_M": 577.94,
   "Q5_K_M": 678.16,
   "Q6_K": 784.7,
   "Q8_0": 1016.12
  }
 },
 "runsWith": [
  "vLLM",
  "SGLang",
  "llama.cpp (Ollama, LM Studio)",
  "MLX (Mac)"
 ],
 "verified": null,
 "updated": "2026-10-10T15:05:26.095Z"
}