dev.cocore.compute.provider

cocore.dev

Samples

100 randomly sampled records from the AT Protocol firehose

dev.cocore.compute.provider (100 samples) 
{
  "os": "macOS 27.0",
  "chip": "Apple M4 Pro",
  "tier": "best-effort",
  "$type": "dev.cocore.compute.provider",
  "ramGB": 48,
  "active": true,
  "eCores": 4,
  "pCores": 8,
  "serving": true,
  "cpuCores": 12,
  "gpuCores": 16,
  "createdAt": "2026-06-25T13:23:07.837541Z",
  "priceList": [
    {
      "modelId": "mlx-community/Qwen2.5-7B-Instruct-4bit",
      "currency": "CC",
      "inputPricePerMTok": 1000000,
      "outputPricePerMTok": 1000000
    },
    {
      "modelId": "mlx-community/Qwen3.5-2B-MLX-4bit",
      "currency": "CC",
      "inputPricePerMTok": 1000000,
      "outputPricePerMTok": 1000000
    },
    {
      "modelId": "mlx-community/gemma-3-4b-it-qat-4bit",
      "currency": "CC",
      "inputPricePerMTok": 1000000,
      "outputPricePerMTok": 1000000
    },
    {
      "modelId": "stub",
      "currency": "CC",
      "inputPricePerMTok": 1000000,
      "outputPricePerMTok": 1000000
    }
  ],
  "trustLevel": "self-attested",
  "engineFault": {
    "at": "2026-06-25T13:23:07.416929Z",
    "code": "model-too-large",
    "models": [
      "mlx-community/Qwen3.6-35B-A3B-4bit"
    ],
    "message": "The configured model(s) [mlx-community/Qwen3.6-35B-A3B-4bit] need more memory than this machine's 48GB of RAM, so they were not loaded. The machine is online but only serving the no-op `stub` engine, so it won't be matched to real inference jobs. Fix: pick a smaller model that fits this machine (the model picker only offers models that fit), or run cocore on a machine with more RAM. If you know this model fits, set COCORE_IGNORE_RAM_FLOOR=1 and start serving again."
  },
  "machineLabel": "nozam MB Pro",
  "provisioning": false,
  "binaryVersion": "0.9.30",
  "modelIdentifier": "Mac16,8",
  "supportedModels": [
    "mlx-community/Qwen2.5-7B-Instruct-4bit",
    "mlx-community/Qwen3.5-2B-MLX-4bit",
    "mlx-community/gemma-3-4b-it-qat-4bit",
    "stub"
  ],
  "encryptionPubKey": "aufx7Y43513BzJsiUPj4HHzFiJ/3wg2x73M3c9L4eUw=",
  "attestationPubKey": "6Nc5dTvEt4uV07AHws99Dyvkvu3L0A7FuJC+DrMaxFJiIqIk8Lps/mXS4uBKEqqHcTL51/3mo0hw5rWO4ajxnA==",
  "memoryBandwidthGBs": 273
}

did:plc:lmkzmvv6sdxntwtyxpg7fqqq | at://did:plc:lmkzmvv6sdxntwtyxpg7fqqq/dev.cocore.compute.provider/3molrphncil2m

Lexicon Garden

@