{
 "id": "intern-s2-397b",
 "name": "Intern S2 397B",
 "repo": "internlm/Intern-S2-397B",
 "lab": {
  "name": "Shanghai AI Lab",
  "country": "China"
 },
 "released": "2026-09-13",
 "parameters": 403.423094768,
 "activeParameters": 18,
 "maxContext": 262144,
 "architecture": "60 layers · 15 full attention (2 KV × 256) · 45 linear attention",
 "page": "https://studiotvai.com/vram-requirements/intern-s2-397b",
 "calculator": "https://studiotvai.com/llm-vram-calculator?model=intern-s2-397b",
 "weightsGiB": {
  "bf16": 739.15,
  "fp8": 371.49,
  "q4_k_m": 223.08
 },
 "kvCacheGiBPerRequest": [
  {
   "context": 8192,
   "bf16": 0.234,
   "fp8": 0.117
  },
  {
   "context": 32768,
   "bf16": 0.938,
   "fp8": 0.469
  },
  {
   "context": 131072,
   "bf16": 3.75,
   "fp8": 1.875
  },
  {
   "context": 262144,
   "bf16": 7.5,
   "fp8": 3.75
  }
 ],
 "recurrentStateGiBPerRequest": 0.1789,
 "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": 48,
     "fp8": 24,
     "q4_k_m": 16
    }
   },
   {
    "gpu": "rtx-5090",
    "name": "GeForce RTX 5090",
    "memoryGB": 32,
    "engine": "llama.cpp",
    "byFormat": {
     "bf16": 32,
     "fp8": 16,
     "q4_k_m": 8
    }
   },
   {
    "gpu": "rtx-pro-6000",
    "name": "RTX PRO 6000 Blackwell",
    "memoryGB": 96,
    "engine": "llama.cpp",
    "byFormat": {
     "bf16": 16,
     "fp8": 5,
     "q4_k_m": 3
    }
   },
   {
    "gpu": "mac-m5-max-128",
    "name": "Mac M5 Max 128 GB",
    "memoryGB": 96,
    "engine": "llama.cpp",
    "byFormat": {
     "bf16": 16,
     "fp8": 5,
     "q4_k_m": 3
    }
   },
   {
    "gpu": "h100",
    "name": "NVIDIA H100",
    "memoryGB": 80,
    "engine": "vLLM",
    "byFormat": {
     "bf16": 16,
     "fp8": 6,
     "q4_k_m": 4
    }
   },
   {
    "gpu": "h200",
    "name": "NVIDIA H200",
    "memoryGB": 141,
    "engine": "vLLM",
    "byFormat": {
     "bf16": 7,
     "fp8": 4,
     "q4_k_m": 2
    }
   },
   {
    "gpu": "b200",
    "name": "NVIDIA B200 (HGX)",
    "memoryGB": 180,
    "engine": "vLLM",
    "byFormat": {
     "bf16": 5,
     "fp8": 3,
     "q4_k_m": 2
    }
   }
  ]
 },
 "ggufFiles": {
  "repo": "bartowski/Intern-S2-397B-GGUF",
  "gib": {
   "IQ1_M": 94.83,
   "IQ1_S": 85.32,
   "IQ2_M": 136.03,
   "IQ2_S": 122.53,
   "IQ2_XS": 116.56,
   "IQ2_XXS": 110.68,
   "IQ3_M": 198.55,
   "IQ3_XS": 169.35,
   "IQ3_XXS": 161.39,
   "IQ4_NL": 235.89,
   "IQ4_XS": 207.94,
   "Q2_K": 143.89,
   "Q3_K_L": 189.94,
   "Q3_K_M": 180.39,
   "Q3_K_S": 171.16,
   "Q4_0": 213.43,
   "Q4_1": 235.46,
   "Q4_K_M": 237.1,
   "Q4_K_S": 220.94,
   "Q5_K_M": 288.11,
   "Q5_K_S": 266.89,
   "Q6_K": 329.27,
   "Q6_K_S": 313.77,
   "Q8_0": 399.18
  }
 },
 "runsWith": [
  "vLLM",
  "SGLang",
  "llama.cpp (Ollama, LM Studio)",
  "MLX (Mac)"
 ],
 "verified": null,
 "updated": "2026-10-10T15:05:26.095Z"
}