{
 "id": "s5-nano",
 "name": "S5-nano",
 "repo": "maritaca-ai/S5-nano",
 "lab": {
  "name": "Maritaca AI",
  "country": "Brazil"
 },
 "released": "2026-11-02",
 "parameters": 4.659865088,
 "activeParameters": null,
 "maxContext": 262144,
 "architecture": "32 layers · 8 full attention (4 KV × 256) · 24 linear attention",
 "page": "https://studiotvai.com/vram-requirements/s5-nano",
 "calculator": "https://studiotvai.com/llm-vram-calculator?model=s5-nano",
 "weightsGiB": {
  "bf16": 8.45,
  "fp8": 4.82,
  "q4_k_m": 2.49
 },
 "kvCacheGiBPerRequest": [
  {
   "context": 8192,
   "bf16": 0.25,
   "fp8": 0.125
  },
  {
   "context": 32768,
   "bf16": 1,
   "fp8": 0.5
  },
  {
   "context": 131072,
   "bf16": 4,
   "fp8": 2
  },
  {
   "context": 262144,
   "bf16": 8,
   "fp8": 4
  }
 ],
 "recurrentStateGiBPerRequest": 0.048,
 "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": "bartowski/maritaca-ai_S5-nano-GGUF",
  "gib": {
   "IQ2_M": 1.54,
   "IQ3_M": 2.18,
   "IQ3_XS": 1.91,
   "IQ3_XXS": 1.84,
   "IQ4_NL": 2.6,
   "IQ4_XS": 2.33,
   "Q2_K": 1.67,
   "Q3_K_L": 2.09,
   "Q3_K_M": 1.99,
   "Q3_K_S": 1.9,
   "Q4_0": 2.53,
   "Q4_1": 2.72,
   "Q4_K_L": 2.77,
   "Q4_K_M": 2.61,
   "Q4_K_S": 2.44,
   "Q5_K_M": 3.13,
   "Q5_K_S": 2.94,
   "Q6_K": 3.5,
   "Q6_K_L": 3.65,
   "Q6_K_S": 3.36,
   "Q8_0": 4.3,
   "BF16": 8.07
  }
 },
 "runsWith": [
  "vLLM",
  "SGLang",
  "llama.cpp (Ollama, LM Studio)",
  "MLX (Mac)"
 ],
 "verified": null,
 "updated": "2026-11-22T00:05:05.824Z"
}
