{
 "id": "deepseek-v4.1-flash",
 "name": "DeepSeek V4.1 Flash",
 "repo": "deepseek-ai/DeepSeek-V4.1-Flash",
 "lab": {
  "name": "DeepSeek",
  "country": "China"
 },
 "released": "2026-09-10",
 "parameters": 763.21,
 "activeParameters": 16,
 "maxContext": 1048576,
 "architecture": "MoE 384 experts · global KV written by 4 of 40 layers and shared by the rest (890 bytes per token in native FP4) + 128-token window · 196B Engram memory",
 "page": "https://studiotvai.com/vram-requirements/deepseek-v4-1-flash",
 "calculator": "https://studiotvai.com/llm-vram-calculator?model=deepseek-v4.1-flash",
 "weightsGiB": {
  "native": 467.86,
  "bf16": 1395.09,
  "fp8": 698.78,
  "q4_k_m": 421.28
 },
 "kvCacheGiBPerRequest": [
  {
   "context": 8192,
   "bf16": 0.027,
   "fp8": 0.016
  },
  {
   "context": 32768,
   "bf16": 0.093,
   "fp8": 0.057
  },
  {
   "context": 131072,
   "bf16": 0.358,
   "fp8": 0.221
  },
  {
   "context": 1048576,
   "bf16": 2.827,
   "fp8": 1.751
  }
 ],
 "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": {
     "native": 24,
     "bf16": 96,
     "fp8": 48,
     "q4_k_m": 24
    }
   },
   {
    "gpu": "rtx-5090",
    "name": "GeForce RTX 5090",
    "memoryGB": 32,
    "engine": "llama.cpp",
    "byFormat": {
     "native": 24,
     "bf16": 64,
     "fp8": 32,
     "q4_k_m": 16
    }
   },
   {
    "gpu": "rtx-pro-6000",
    "name": "RTX PRO 6000 Blackwell",
    "memoryGB": 96,
    "engine": "llama.cpp",
    "byFormat": {
     "native": 6,
     "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": {
     "native": 6,
     "bf16": 16,
     "fp8": 8,
     "q4_k_m": 5
    }
   },
   {
    "gpu": "h100",
    "name": "NVIDIA H100",
    "memoryGB": 80,
    "engine": "vLLM",
    "byFormat": {
     "native": 7,
     "bf16": 24,
     "fp8": 16,
     "q4_k_m": 7
    }
   },
   {
    "gpu": "h200",
    "name": "NVIDIA H200",
    "memoryGB": 141,
    "engine": "vLLM",
    "byFormat": {
     "native": 4,
     "bf16": 16,
     "fp8": 6,
     "q4_k_m": 4
    }
   },
   {
    "gpu": "b200",
    "name": "NVIDIA B200 (HGX)",
    "memoryGB": 180,
    "engine": "vLLM",
    "byFormat": {
     "native": 3,
     "bf16": 16,
     "fp8": 5,
     "q4_k_m": 3
    }
   }
  ]
 },
 "ggufFiles": {
  "repo": "vcruz305/DeepSeek-V4.1-Flash-GGUF",
  "gib": {
   "Q2_K": 246.35,
   "Q3_K_M": 323.42,
   "Q4_K_M": 414.19,
   "Q8_0": 473.07
  }
 },
 "runsWith": [
  "vLLM",
  "MLX (Mac)"
 ],
 "verified": null,
 "updated": "2026-10-10T15:05:26.095Z"
}