~/llamay $ llamay serve -m gemma2:2b -addr 127.0.0.1:11439
time=2026-09-18T08:49:46.415-04:00 level=INFO msg="device graph attached" max-tokens=256
time=2026-09-18T08:49:46.415-04:00 level=INFO msg="llamay serving" addr=127.0.0.1:11439 mode
l=gemma2:2b arch=gemma2 max-loaded=2 keepalive=5m0s params="1.59 GB" context=8192 threads=7
kv=f32 lexicon=0

  OpenAI      POST http://127.0.0.1:11439/v1/chat/completions
  Anthropic   POST http://127.0.0.1:11439/v1/messages
  Embeddings  POST http://127.0.0.1:11439/v1/embeddings     (start with -embed <encoder.gguf
>)
  Rerank      POST http://127.0.0.1:11439/rerank            (start with -rerank <reranker.gg
uf>)
  Contexts    POST http://127.0.0.1:11439/v1/contexts        (then /{id}/fork?n=8, /{id}/sna
pshot)
  Models      POST http://127.0.0.1:11439/api/pull          (and /api/copy, /api/delete)
  Stats       GET  http://127.0.0.1:11439/v1/stats


~/llamay $ # the server stays up; the rest of this is a second terminal
~/llamay $ curl -s http://127.0.0.1:11439/v1/chat/completions -H 'content-type: application/
json' -d '{
>   "model": "gemma2:2b",
>   "messages": [{"role":"user","content":"What is the weather in Pune?"}],
>   "tools": [{"type":"function","function":{
>     "name": "get_weather",
>     "parameters": {"type":"object",
>       "properties": {"city":{"type":"string"},
>                      "unit":{"enum":["c","f"]}},
>       "required": ["city","unit"]}}}]
> }' | jq '.choices[0].message.tool_calls'
[
  {
    "function": {
      "arguments": "{\"city\":\"Pune\",\"unit\":\"c\"}",
      "name": "get_weather"
    },
    "id": "call_949aba1576ea",
    "index": 0,
    "type": "function"
  }
]
~/llamay $ # city is a string and unit is one of two letters, because it could not be otherw
ise