{
 "id": "ernie-5.5-flash-base",
 "name": "ERNIE 5.5 Flash Base",
 "repo": "baidu/ERNIE-5.5-Flash-Base",
 "lab": {
  "name": "Baidu",
  "country": "China"
 },
 "released": "2026-10-21",
 "parameters": 286.25,
 "activeParameters": 14,
 "maxContext": 1048576,
 "architecture": "MoE 512 latent experts + 1 shared · 37 compressed-attention layers (128-token window + 128× compression, 512-wide) · 6 sparse MLA layers (512 + 64 latent, indexer keys)",
 "page": "https://studiotvai.com/vram-requirements/ernie-5-5-flash-base",
 "calculator": "https://studiotvai.com/llm-vram-calculator?model=ernie-5.5-flash-base",
 "weightsGiB": {
  "native": 262.42,
  "bf16": 520.79,
  "fp8": 261.93,
  "q4_k_m": 157.38
 },
 "kvCacheGiBPerRequest": [
  {
   "context": 8192,
   "bf16": 0.066,
   "fp8": 0.04
  },
  {
   "context": 32768,
   "bf16": 0.249,
   "fp8": 0.152
  },
  {
   "context": 131072,
   "bf16": 0.981,
   "fp8": 0.6
  },
  {
   "context": 1048576,
   "bf16": 7.817,
   "fp8": 4.785
  }
 ],
 "recurrentStateGiBPerRequest": 0.0181,
 "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": 32,
     "fp8": 16,
     "q4_k_m": 8
    }
   },
   {
    "gpu": "rtx-5090",
    "name": "GeForce RTX 5090",
    "memoryGB": 32,
    "engine": "llama.cpp",
    "byFormat": {
     "native": 16,
     "bf16": 24,
     "fp8": 16,
     "q4_k_m": 6
    }
   },
   {
    "gpu": "rtx-pro-6000",
    "name": "RTX PRO 6000 Blackwell",
    "memoryGB": 96,
    "engine": "llama.cpp",
    "byFormat": {
     "native": 3,
     "bf16": 6,
     "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": 6,
     "fp8": 3,
     "q4_k_m": 2
    }
   },
   {
    "gpu": "strix-halo",
    "name": "Ryzen AI Max+ 395 128 GB",
    "memoryGB": 96,
    "engine": "llama.cpp",
    "byFormat": {
     "native": 3,
     "bf16": 6,
     "fp8": 3,
     "q4_k_m": 2
    }
   },
   {
    "gpu": "dgx-spark",
    "name": "DGX Spark (GB10)",
    "memoryGB": 128,
    "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": 8,
     "fp8": 4,
     "q4_k_m": 3
    }
   },
   {
    "gpu": "h200",
    "name": "NVIDIA H200",
    "memoryGB": 141,
    "engine": "vLLM",
    "byFormat": {
     "native": 3,
     "bf16": 5,
     "fp8": 3,
     "q4_k_m": 2
    }
   },
   {
    "gpu": "b200",
    "name": "NVIDIA B200 (HGX)",
    "memoryGB": 180,
    "engine": "vLLM",
    "byFormat": {
     "native": 2,
     "bf16": 4,
     "fp8": 2,
     "q4_k_m": 2
    }
   }
  ]
 },
 "ggufFiles": null,
 "runsWith": [
  "vLLM"
 ],
 "verified": null,
 "updated": "2026-11-06T21:02:26.190Z"
}