{
 "id": "qwen3-coder-next",
 "name": "Qwen3-Coder-Next 80B-A3B",
 "repo": "Qwen/Qwen3-Coder-Next",
 "lab": {
  "name": "Alibaba",
  "country": "China"
 },
 "released": "2026-01-30",
 "parameters": 79.67,
 "activeParameters": 3,
 "maxContext": 262144,
 "architecture": "MoE 512 experts · KV on 12 of 48 layers (GQA, 2 KV heads × 256) · 36 Gated DeltaNet layers",
 "page": "https://studiotvai.com/vram-requirements/qwen3-coder-next",
 "calculator": "https://studiotvai.com/llm-vram-calculator?model=qwen3-coder-next",
 "weightsGiB": {
  "bf16": 148.4,
  "fp8": 74.78,
  "q4_k_m": 44.86
 },
 "kvCacheGiBPerRequest": [
  {
   "context": 8192,
   "bf16": 0.188,
   "fp8": 0.094
  },
  {
   "context": 32768,
   "bf16": 0.75,
   "fp8": 0.375
  },
  {
   "context": 131072,
   "bf16": 3,
   "fp8": 1.5
  },
  {
   "context": 262144,
   "bf16": 6,
   "fp8": 3
  }
 ],
 "recurrentStateGiBPerRequest": 0.072,
 "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": 7,
     "fp8": 4,
     "q4_k_m": 3
    }
   },
   {
    "gpu": "rtx-5090",
    "name": "GeForce RTX 5090",
    "memoryGB": 32,
    "engine": "llama.cpp",
    "byFormat": {
     "bf16": 6,
     "fp8": 3,
     "q4_k_m": 2
    }
   },
   {
    "gpu": "rtx-pro-6000",
    "name": "RTX PRO 6000 Blackwell",
    "memoryGB": 96,
    "engine": "llama.cpp",
    "byFormat": {
     "bf16": 2,
     "fp8": 1,
     "q4_k_m": 1
    }
   },
   {
    "gpu": "mac-m5-max-128",
    "name": "Mac M5 Max 128 GB",
    "memoryGB": 96,
    "engine": "llama.cpp",
    "byFormat": {
     "bf16": 2,
     "fp8": 1,
     "q4_k_m": 1
    }
   },
   {
    "gpu": "h100",
    "name": "NVIDIA H100",
    "memoryGB": 80,
    "engine": "vLLM",
    "byFormat": {
     "bf16": 3,
     "fp8": 2,
     "q4_k_m": 1
    }
   },
   {
    "gpu": "h200",
    "name": "NVIDIA H200",
    "memoryGB": 141,
    "engine": "vLLM",
    "byFormat": {
     "bf16": 2,
     "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": "unsloth/Qwen3-Coder-Next-GGUF",
  "gib": {
   "BF16": 148.51,
   "Q4_1": 46.62,
   "Q5_K_M": 52.94,
   "Q5_K_S": 51.27,
   "Q6_K": 61.11,
   "Q8_0": 78.99,
   "IQ4_NL": 42.03,
   "IQ4_XS": 39.75,
   "MXFP4_MOE": 44.73,
   "Q2_K": 27.22,
   "Q2_K_L": 27.29,
   "Q3_K_M": 35.69,
   "Q3_K_S": 32.23,
   "Q4_0": 42.22,
   "Q4_K_M": 45.2,
   "Q4_K_S": 42.4,
   "UD-IQ1_M": 20.21,
   "UD-IQ1_S": 20.03,
   "UD-IQ2_M": 23.25,
   "UD-IQ2_XXS": 21.71,
   "UD-IQ3_S": 27.65,
   "UD-IQ3_XXS": 26.53,
   "UD-IQ4_NL": 36.54,
   "UD-IQ4_XS": 35.79,
   "UD-Q2_K_XL": 24.92,
   "UD-Q3_K_M": 33.47,
   "UD-Q3_K_S": 31.03,
   "UD-Q3_K_XL": 33.79,
   "UD-Q4_K_M": 45.92,
   "UD-Q4_K_S": 42.92,
   "UD-Q4_K_XL": 46.2,
   "UD-TQ1_0": 17.64,
   "UD-Q5_K_M": 55.17,
   "UD-Q5_K_S": 51.99,
   "UD-Q5_K_XL": 55.45,
   "UD-Q6_K": 61.27,
   "UD-Q6_K_XL": 68.1,
   "UD-Q8_K_XL": 80.42
  }
 },
 "runsWith": [
  "vLLM",
  "SGLang",
  "llama.cpp (Ollama, LM Studio)",
  "MLX (Mac)"
 ],
 "verified": null,
 "updated": "2026-10-10T15:05:26.095Z"
}