~/llamay $ llamay serve -m qwen2.5:0.5b -addr 127.0.0.1:11439
time=2026-09-18T08:49:09.326-04:00 level=INFO msg="device graph attached" max-tokens=256
time=2026-09-18T08:49:09.326-04:00 level=INFO msg="llamay serving" addr=127.0.0.1:11439 mode
l=qwen2.5:0.5b arch=qwen2 max-loaded=2 keepalive=5m0s params="0.36 GB" context=32768 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/models | jq
{
  "data": [
    {
      "created": 1789735749,
      "id": "all-minilm:latest",
      "object": "model",
      "owned_by": "azmx"
    },
    {
      "created": 1789735749,
      "id": "gemma2:2b",
      "object": "model",
      "owned_by": "azmx"
    },
    {
      "created": 1789735749,
      "id": "gemma3:270m",
      "object": "model",
      "owned_by": "azmx"
    },
    {
      "created": 1789735749,
      "id": "gpt2:q8_0",
      "object": "model",
      "owned_by": "azmx"
    },
    {
      "created": 1789735749,
      "id": "qwen2.5:0.5b",
      "object": "model",
      "owned_by": "azmx"
    },
    {
      "created": 1789735749,
      "id": "smollm2:135m",
      "object": "model",
      "owned_by": "azmx"
    },
    {
      "created": 1789735749,
      "id": "azmx-code-test:latest",
      "object": "model",
      "owned_by": "azmx"
    }
  ],
  "object": "list"
}
~/llamay $ curl -s http://127.0.0.1:11439/v1/chat/completions -H 'content-type: application/
json' \
>   -d '{"model":"qwen2.5:0.5b","messages":[{"role":"user","content":"One sentence: why run
a model locally?"}]}' | jq
{
  "choices": [
    {
      "finish_reason": "stop",
      "index": 0,
      "message": {
        "content": "running a model locally can be beneficial because it allows you to optim
ize the model locally, which can be faster and more efficient compared to running the model
globally.",
        "role": "assistant"
      }
    }
  ],
  "created": 1789735751,
  "id": "chatcmpl-llamay",
  "model": "qwen2.5:0.5b",
  "object": "chat.completion",
  "usage": {
    "completion_tokens": 31,
    "llamay_cached_prompt_tokens": 0,
    "llamay_decode_ms": 1528.48,
    "llamay_prefill_ms": 153.028,
    "prompt_tokens": 17,
    "prompt_tokens_details": {
      "cached_tokens": 0
    },
    "total_tokens": 48
  }
}
~/llamay $ # the same route with stream:true — this is the wire format
~/llamay $ curl -sN http://127.0.0.1:11439/v1/chat/completions -H 'content-type: application
/json' \
>   -d '{"model":"qwen2.5:0.5b","stream":true,"messages":[{"role":"user","content":"Count to
 five."}]}' | head -c 520
data: {"choices":[{"delta":{"content":"Count"},"finish_reason":null,"index":0}],"created":17
89735751,"id":"chatcmpl-llamay","model":"qwen2.5:0.5b","object":"chat.completion.chunk"}

data: {"choices":[{"delta":{"content":"ing"},"finish_reason":null,"index":0}],"created":1789
735751,"id":"chatcmpl-llamay","model":"qwen2.5:0.5b","object":"chat.completion.chunk"}

data: {"choices":[{"delta":{"content":" to"},"finish_reason":null,"index":0}],"created":1789
735751,"id":"chatcmpl-llamay","model":"qwen2.5:0.5b","object":"cha~/llamay $ # and the same
stream read the way a client reads it
~/llamay $ curl -sN http://127.0.0.1:11439/v1/chat/completions -H 'content-type: application
/json' \
>   -d '{"model":"qwen2.5:0.5b","stream":true,"messages":[{"role":"user","content":"Count to
 five, then stop."}]}' \
>   | python3 scripts/site/demo_sse.py
1
2
3
4
5