{
 "id": "unlimited-ocr",
 "name": "Unlimited-OCR",
 "repo": "baidu/Unlimited-OCR",
 "lab": {
  "name": "Baidu",
  "country": "China"
 },
 "released": "2026-06-19",
 "parameters": 3.33610624,
 "activeParameters": 0.7,
 "maxContext": 32768,
 "architecture": "12 layers · 12 sliding-window layers (128 tokens, 10 KV × 128)",
 "page": "https://studiotvai.com/vram-requirements/unlimited-ocr",
 "calculator": "https://studiotvai.com/llm-vram-calculator?model=unlimited-ocr",
 "weightsGiB": {
  "bf16": 6.21,
  "fp8": 3.42,
  "q4_k_m": 1.85
 },
 "kvCacheGiBPerRequest": [
  {
   "context": 8192,
   "bf16": 0.007,
   "fp8": 0.004
  },
  {
   "context": 32768,
   "bf16": 0.007,
   "fp8": 0.004
  }
 ],
 "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": {
     "bf16": 1,
     "fp8": 1,
     "q4_k_m": 1
    }
   },
   {
    "gpu": "rtx-5090",
    "name": "GeForce RTX 5090",
    "memoryGB": 32,
    "engine": "llama.cpp",
    "byFormat": {
     "bf16": 1,
     "fp8": 1,
     "q4_k_m": 1
    }
   },
   {
    "gpu": "rtx-pro-6000",
    "name": "RTX PRO 6000 Blackwell",
    "memoryGB": 96,
    "engine": "llama.cpp",
    "byFormat": {
     "bf16": 1,
     "fp8": 1,
     "q4_k_m": 1
    }
   },
   {
    "gpu": "mac-m5-max-128",
    "name": "Mac M5 Max 128 GB",
    "memoryGB": 96,
    "engine": "llama.cpp",
    "byFormat": {
     "bf16": 1,
     "fp8": 1,
     "q4_k_m": 1
    }
   },
   {
    "gpu": "strix-halo",
    "name": "Ryzen AI Max+ 395 128 GB",
    "memoryGB": 96,
    "engine": "llama.cpp",
    "byFormat": {
     "bf16": 1,
     "fp8": 1,
     "q4_k_m": 1
    }
   },
   {
    "gpu": "dgx-spark",
    "name": "DGX Spark (GB10)",
    "memoryGB": 128,
    "engine": "llama.cpp",
    "byFormat": {
     "bf16": 1,
     "fp8": 1,
     "q4_k_m": 1
    }
   },
   {
    "gpu": "h100",
    "name": "NVIDIA H100",
    "memoryGB": 80,
    "engine": "vLLM",
    "byFormat": {
     "bf16": 1,
     "fp8": 1,
     "q4_k_m": 1
    }
   },
   {
    "gpu": "h200",
    "name": "NVIDIA H200",
    "memoryGB": 141,
    "engine": "vLLM",
    "byFormat": {
     "bf16": 1,
     "fp8": 1,
     "q4_k_m": 1
    }
   },
   {
    "gpu": "b200",
    "name": "NVIDIA B200 (HGX)",
    "memoryGB": 180,
    "engine": "vLLM",
    "byFormat": {
     "bf16": 1,
     "fp8": 1,
     "q4_k_m": 1
    }
   }
  ]
 },
 "ggufFiles": {
  "repo": "sahilchachra/Unlimited-OCR-GGUF",
  "gib": {
   "BF16": 5.47,
   "IQ2_M": 1.15,
   "IQ3_M": 1.35,
   "IQ3_XXS": 1.24,
   "IQ4_NL": 1.59,
   "IQ4_XS": 1.53,
   "Q3_K_M": 1.45,
   "Q4_K_M": 1.82,
   "Q4_K_S": 1.68,
   "Q5_K_M": 2.07,
   "Q5_K_S": 1.95,
   "Q6_K": 2.43,
   "Q8_0": 2.91
  }
 },
 "runsWith": [
  "vLLM",
  "SGLang",
  "llama.cpp (Ollama, LM Studio)",
  "MLX (Mac)"
 ],
 "verified": null,
 "updated": "2026-10-16T00:03:05.821Z"
}