Card: FluidUse demos (topic sort, audio search, code search)

README.md

@@ -123,4 +123,14 @@ The model card warns against fp16: activations reach ~2,000, so squaring them in
 RMSNorm here divides by the row's max-abs value first, which keeps the math in range (plain fp16 RMSNorm: cosine
 0.95 to the reference; this conversion: 0.9996). The final normalization is rescaled the same way.
 
+## Demos ([FluidUse](https://github.com/FluidInference/FluidUse), M5 Pro)
+
+| Demo | What it shows |
+|---|---|
+| `TopicSortDemo` | 10,080 posts sorted into topics live (~600 posts/s); split any topic into subtopics |
+| `AudioSearchDemo` | 4.5 h of audio indexed in 38 s (431× real time, audio on the GPU + text on the Neural Engine at once); eight text searches each return the right three clips (sound files under random names); ~710 searches/s |
+| `CodeSearchDemo` | 5,617 FluidAudio functions indexed in 16 s; plain-English questions find the right function where an exact-phrase grep finds nothing; ~700 searches/s |
+
+Each runs as a short show: `Sources/<Demo>/demo.sh`, then Play.
+
 License: Apache 2.0, same as the source model.