inferrs serve gg-hf-gg/gemma-4-E2B-it \
  --host 127.0.0.1 \
  --port 8080 \
  --device metal

curl http://127.0.0.1:8080/health
curl http://127.0.0.1:8080/v1/models

{
  agents: {
    defaults: {
      model: { primary: "inferrs/gg-hf-gg/gemma-4-E2B-it" },
      models: {
        "inferrs/gg-hf-gg/gemma-4-E2B-it": {
          alias: "Gemma 4 (inferrs)",
        },
      },
    },
  },
  models: {
    mode: "merge",
    providers: {
      inferrs: {
        baseUrl: "http://127.0.0.1:8080/v1",
        apiKey: "inferrs-local",
        api: "openai-completions",
        models: [
          {
            id: "gg-hf-gg/gemma-4-E2B-it",
            name: "Gemma 4 E2B (inferrs)",
            reasoning: false,
            input: ["text"],
            cost: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0 },
            contextWindow: 131072,
            maxTokens: 4096,
            compat: {
              requiresStringContent: true,
            },
          },
        ],
      },
    },
  },
}

messages[1].content: invalid type: sequence, expected a string

compat: {
  requiresStringContent: true
}

compat: {
  requiresStringContent: true,
  supportsTools: false
}

curl http://127.0.0.1:8080/v1/chat/completions \
  -H 'content-type: application/json' \
  -d '{"model":"gg-hf-gg/gemma-4-E2B-it","messages":[{"role":"user","content":"What is 2 + 2?"}],"stream":false}'

openclaw infer model run \
  --model inferrs/gg-hf-gg/gemma-4-E2B-it \
  --prompt "What is 2 + 2? Reply with one short sentence." \
  --json