{
 "id": "mistral-nemo",
 "name": "Mistral-Nemo",
 "repo": "mistralai/Mistral-Nemo-Instruct-2407",
 "lab": {
  "name": "Mistral AI",
  "country": "France"
 },
 "released": "2024-07-17",
 "parameters": 12.2477824,
 "activeParameters": null,
 "maxContext": 131072,
 "architecture": "40 layers · 40 full attention (8 KV × 128)",
 "page": "https://studiotvai.com/vram-requirements/mistral-nemo",
 "calculator": "https://studiotvai.com/llm-vram-calculator?model=mistral-nemo",
 "weightsGiB": {
  "bf16": 22.81,
  "fp8": 12.66,
  "q4_k_m": 7.02
 },
 "kvCacheGiBPerRequest": [
  {
   "context": 8192,
   "bf16": 1.25,
   "fp8": 0.625
  },
  {
   "context": 32768,
   "bf16": 5,
   "fp8": 2.5
  },
  {
   "context": 131072,
   "bf16": 20,
   "fp8": 10
  }
 ],
 "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": 2,
     "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": "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": "MaziyarPanahi/Mistral-Nemo-Instruct-2407-GGUF",
  "gib": {
   "Q2_K": 4.46,
   "Q3_K_L": 6.11,
   "Q3_K_M": 5.67,
   "Q3_K_S": 5.15,
   "Q4_K_M": 6.96,
   "Q4_K_S": 6.63,
   "Q5_K_M": 8.13,
   "Q5_K_S": 7.93,
   "Q6_K": 9.37,
   "Q8_0": 12.13
  }
 },
 "runsWith": [
  "vLLM",
  "SGLang",
  "llama.cpp (Ollama, LM Studio)",
  "MLX (Mac)"
 ],
 "verified": {
  "gguf": {
   "day": "2026-10-11",
   "repo": "MaziyarPanahi/Mistral-Nemo-Instruct-2407-GGUF",
   "kv": "match",
   "ours": 163840,
   "theirs": 163840
  }
 },
 "updated": "2026-10-11T19:08:05.666Z"
}