{
 "id": "atria-dawn-preview",
 "name": "Atria Dawn Preview",
 "repo": "internlm/Atria-Dawn-Preview",
 "lab": {
  "name": "Shanghai AI Lab",
  "country": "China"
 },
 "released": "2026-09-11",
 "parameters": 753.32994048,
 "activeParameters": 42,
 "maxContext": 1048576,
 "architecture": "78 layers · MLA (512 + 64 latent) on 78 · indexer keys on 21",
 "page": "https://studiotvai.com/vram-requirements/atria-dawn-preview",
 "calculator": "https://studiotvai.com/llm-vram-calculator?model=atria-dawn-preview",
 "weightsGiB": {
  "bf16": 1384.65,
  "fp8": 694.1,
  "q4_k_m": 418.18
 },
 "kvCacheGiBPerRequest": [
  {
   "context": 8192,
   "bf16": 0.707,
   "fp8": 0.412
  },
  {
   "context": 32768,
   "bf16": 2.827,
   "fp8": 1.646
  },
  {
   "context": 131072,
   "bf16": 11.307,
   "fp8": 6.584
  },
  {
   "context": 1048576,
   "bf16": 90.457,
   "fp8": 52.676
  }
 ],
 "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": null,
 "runsWith": [
  "vLLM",
  "SGLang",
  "llama.cpp (Ollama, LM Studio)",
  "MLX (Mac)"
 ],
 "verified": null,
 "updated": "2026-10-10T15:05:26.095Z"
}