{
 "id": "glm-5",
 "name": "GLM-5",
 "repo": "zai-org/GLM-5",
 "lab": {
  "name": "Z.ai",
  "country": "China"
 },
 "released": "2026-02-11",
 "parameters": 753.864139008,
 "activeParameters": 42,
 "maxContext": 202752,
 "architecture": "78 layers · MLA (512 + 64 latent) on 78 · indexer keys on 78",
 "page": "https://studiotvai.com/vram-requirements/glm-5",
 "calculator": "https://studiotvai.com/llm-vram-calculator?model=glm-5",
 "weightsGiB": {
  "bf16": 1385.64,
  "fp8": 694.59,
  "q4_k_m": 418.48
 },
 "kvCacheGiBPerRequest": [
  {
   "context": 8192,
   "bf16": 0.764,
   "fp8": 0.469
  },
  {
   "context": 32768,
   "bf16": 3.056,
   "fp8": 1.876
  },
  {
   "context": 131072,
   "bf16": 12.226,
   "fp8": 7.503
  },
  {
   "context": 202752,
   "bf16": 18.911,
   "fp8": 11.606
  }
 ],
 "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": 96,
     "fp8": 48,
     "q4_k_m": 24
    }
   },
   {
    "gpu": "rtx-5090",
    "name": "GeForce RTX 5090",
    "memoryGB": 32,
    "engine": "llama.cpp",
    "byFormat": {
     "bf16": 64,
     "fp8": 32,
     "q4_k_m": 16
    }
   },
   {
    "gpu": "rtx-pro-6000",
    "name": "RTX PRO 6000 Blackwell",
    "memoryGB": 96,
    "engine": "llama.cpp",
    "byFormat": {
     "bf16": 16,
     "fp8": 8,
     "q4_k_m": 5
    }
   },
   {
    "gpu": "mac-m5-max-128",
    "name": "Mac M5 Max 128 GB",
    "memoryGB": 96,
    "engine": "llama.cpp",
    "byFormat": {
     "bf16": 16,
     "fp8": 8,
     "q4_k_m": 5
    }
   },
   {
    "gpu": "h100",
    "name": "NVIDIA H100",
    "memoryGB": 80,
    "engine": "vLLM",
    "byFormat": {
     "bf16": 24,
     "fp8": 16,
     "q4_k_m": 7
    }
   },
   {
    "gpu": "h200",
    "name": "NVIDIA H200",
    "memoryGB": 141,
    "engine": "vLLM",
    "byFormat": {
     "bf16": 16,
     "fp8": 6,
     "q4_k_m": 4
    }
   },
   {
    "gpu": "b200",
    "name": "NVIDIA B200 (HGX)",
    "memoryGB": 180,
    "engine": "vLLM",
    "byFormat": {
     "bf16": 16,
     "fp8": 5,
     "q4_k_m": 3
    }
   }
  ]
 },
 "ggufFiles": {
  "repo": "unsloth/GLM-5-GGUF",
  "gib": {
   "BF16": 1404.42,
   "UD-TQ1_0": 164.05,
   "IQ4_NL": 396.67,
   "IQ4_XS": 375.23,
   "MXFP4_MOE": 382.36,
   "Q2_K": 257,
   "Q2_K_L": 257.21,
   "Q3_K_M": 335.56,
   "Q3_K_S": 303.87,
   "Q4_0": 397.81,
   "Q4_1": 440.24,
   "Q4_K_M": 424.57,
   "Q4_K_S": 398.95,
   "Q5_K_M": 498.42,
   "Q5_K_S": 484.04,
   "Q6_K": 576.84,
   "Q8_0": 746.31,
   "UD-IQ1_M": 208.48,
   "UD-IQ1_S": 189.71,
   "UD-IQ2_M": 237.27,
   "UD-IQ2_XXS": 224.52,
   "UD-IQ3_XXS": 283.62,
   "UD-Q2_K_XL": 262.06,
   "UD-Q3_K_XL": 309.63,
   "UD-Q4_K_XL": 401.13,
   "UD-Q5_K_XL": 499.4,
   "UD-Q6_K_XL": 600.85,
   "UD-Q8_K_XL": 809.11
  }
 },
 "runsWith": [
  "vLLM",
  "SGLang",
  "llama.cpp (Ollama, LM Studio)"
 ],
 "verified": null,
 "updated": "2026-10-11T19:08:05.666Z"
}