{
 "id": "qwen3.8-flash-next",
 "name": "Qwen3.8-Flash-Next",
 "repo": "Qwen/Qwen3.8-Flash-Next",
 "lab": {
  "name": "Alibaba",
  "country": "China"
 },
 "released": "2026-08-24",
 "parameters": 180,
 "activeParameters": 6,
 "maxContext": 262144,
 "architecture": "MoE 512 experts · 12 Qwen Sparse Attention layers (GQA, 2 KV × 256, + indexer keys per 4-token block) · 36 Gated DeltaNet layers · 51B n-gram embeddings",
 "page": "https://studiotvai.com/vram-requirements/qwen3-8-flash-next",
 "calculator": "https://studiotvai.com/llm-vram-calculator?model=qwen3.8-flash-next",
 "weightsGiB": {
  "bf16": 330.42,
  "fp8": 166.39,
  "q4_k_m": 105.07
 },
 "kvCacheGiBPerRequest": [
  {
   "context": 8192,
   "bf16": 0.193,
   "fp8": 0.1
  },
  {
   "context": 32768,
   "bf16": 0.773,
   "fp8": 0.398
  },
  {
   "context": 131072,
   "bf16": 3.094,
   "fp8": 1.594
  },
  {
   "context": 262144,
   "bf16": 6.188,
   "fp8": 3.188
  }
 ],
 "recurrentStateGiBPerRequest": 0.1075,
 "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": 16,
     "fp8": 8,
     "q4_k_m": 5
    }
   },
   {
    "gpu": "rtx-5090",
    "name": "GeForce RTX 5090",
    "memoryGB": 32,
    "engine": "llama.cpp",
    "byFormat": {
     "bf16": 16,
     "fp8": 6,
     "q4_k_m": 4
    }
   },
   {
    "gpu": "rtx-pro-6000",
    "name": "RTX PRO 6000 Blackwell",
    "memoryGB": 96,
    "engine": "llama.cpp",
    "byFormat": {
     "bf16": 4,
     "fp8": 2,
     "q4_k_m": 2
    }
   },
   {
    "gpu": "mac-m5-max-128",
    "name": "Mac M5 Max 128 GB",
    "memoryGB": 96,
    "engine": "llama.cpp",
    "byFormat": {
     "bf16": 4,
     "fp8": 2,
     "q4_k_m": 2
    }
   },
   {
    "gpu": "h100",
    "name": "NVIDIA H100",
    "memoryGB": 80,
    "engine": "vLLM",
    "byFormat": {
     "bf16": 5,
     "fp8": 3,
     "q4_k_m": 2
    }
   },
   {
    "gpu": "h200",
    "name": "NVIDIA H200",
    "memoryGB": 141,
    "engine": "vLLM",
    "byFormat": {
     "bf16": 3,
     "fp8": 2,
     "q4_k_m": 1
    }
   },
   {
    "gpu": "b200",
    "name": "NVIDIA B200 (HGX)",
    "memoryGB": 180,
    "engine": "vLLM",
    "byFormat": {
     "bf16": 3,
     "fp8": 2,
     "q4_k_m": 1
    }
   }
  ]
 },
 "ggufFiles": {
  "repo": "unsloth/Qwen3.8-Flash-Next-GGUF",
  "gib": {
   "BF16": 329.72,
   "Q8_0": 175.3,
   "UD-IQ1_M": 69.42,
   "UD-IQ1_S": 67.56,
   "UD-IQ3_XXS": 76.33,
   "UD-IQ4_XS": 87.25,
   "UD-Q2_K_XL": 73.45,
   "UD-Q3_K_XL": 83.81,
   "UD-Q4_K_XL": 103.69,
   "UD-Q5_K_XL": 147.42,
   "UD-Q6_K_XL": 157.55
  }
 },
 "runsWith": [
  "vLLM",
  "SGLang",
  "llama.cpp (Ollama, LM Studio)",
  "MLX (Mac)"
 ],
 "verified": null,
 "updated": "2026-10-10T15:05:26.095Z"
}