{
 "id": "qwen3.5-4b-qwenputer",
 "name": "Qwen3.5 4B-Qwenputer",
 "repo": "divagr1925/Qwen3.5-4B-Qwenputer",
 "lab": {
  "name": "Divyansh Agrawal (independent)",
  "country": null
 },
 "released": "2026-10-19",
 "parameters": 9.357602496,
 "activeParameters": null,
 "maxContext": 262144,
 "architecture": "43 layers · 8 full attention (4 KV × 256) · 35 linear attention",
 "page": "https://studiotvai.com/vram-requirements/qwen3-5-4b-qwenputer",
 "calculator": "https://studiotvai.com/llm-vram-calculator?model=qwen3.5-4b-qwenputer",
 "weightsGiB": {
  "bf16": 17.43,
  "fp8": 10.48,
  "q4_k_m": 6.77
 },
 "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": 0.07,
 "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": null,
 "runsWith": [
  "vLLM",
  "SGLang",
  "llama.cpp (Ollama, LM Studio)"
 ],
 "verified": null,
 "updated": "2026-11-05T00:08:05.925Z"
}