Expose conditional KV calculator in Space metadata

README.md

@@ -19,6 +19,7 @@ tags:
   - visualization
   - mixture-of-experts
   - attention
+  - kv-cache
   - recurrent-memory
   - qwen
   - flint
@@ -43,6 +44,8 @@ Explore two different architectures with real Q8_0 tensor captures: Flint's spar
 
 The page also calculates raw f16 full-attention K/V storage across context lengths if a runtime enables caching. Nanbeige's released config sets `use_cache: false`, so this is a conditional calculation rather than measured default memory use.
 
+[Try the conditional 32K calculation](https://alphabell-model-observatory.static.hf.space/architecture/index.html?tokens=32768#kv-title) and move the slider to share another context length.
+
 [Read the architecture explainer](https://huggingface.co/blog/alphabell/nanbeige-qwen-layer-map) for pinned sources and a matched runtime test that could measure how context length affects each model.
 
 ## Five measured experiments