Link the Space to the GGUF model card

README.md

@@ -4,12 +4,22 @@ colorFrom: indigo
 colorTo: pink
 sdk: static
 app_file: index.html
+pinned: false
 fullWidth: true
-short_description: Chat with the Q8_0 Humanlike model through its public API.
+short_description: Chat with the hosted Qwen3.8 Humanlike endpoint.
 models:
-  - LessThanThreeAI/Qwen3.8-27B-Humanlike-Chat-Q8_0-GGUF
+  - LessThanThreeAI/Qwen3.8-27B-Humanlike-Chat-GGUF
 ---
 
 # Qwen3.8 27B Humanlike Chat
 
-Chat client for the public OpenAI-compatible inference endpoint.
+Static chat client for the hosted OpenAI-compatible endpoint at `https://api.lessthanthreeai.com/v1`.
+
+- Model: `qwen3.8-27b-humanlike-chat`
+- No API key required
+- Requests send only `model`, `messages`, `stream`, and `max_tokens`, so the endpoint defaults match the deployment gate
+- Thinking is off by default
+
+The service runs on scale-to-zero capacity. The first message after an idle period can take about two to three minutes while a worker starts, and the request stays connected while that happens. Later messages are fast until the worker shuts down after five idle minutes.
+
+See the [model card](https://huggingface.co/LessThanThreeAI/Qwen3.8-27B-Humanlike-Chat-GGUF) for the artifacts and the [serving configuration](https://huggingface.co/LessThanThreeAI/Qwen3.8-27B-Humanlike-Chat-GGUF/blob/main/SERVING.md) for the engine setup.