Update README.md

README.md

@@ -27,15 +27,13 @@ pipeline_tag: text-generation
 
 </div>
 
-This repository hosts the **edge0-35b** checkpoint of the
-[edge0](https://github.com/Edge0-AI/edge0) streaming MoE inference
-framework. The full 4-bit checkpoint (≈23 GB) stays on storage; edge0
-mmaps it and streams MoE experts from SSD on demand, with a trained
-**prerouter** head that predicts the next token's expert routing one
-step ahead so expert loads hide completely behind the forward pass. The
-result: **a 35B-A3B MoE with ≈2.9 GiB of active memory** — small enough
-for phone-class memory budgets, with no upfront weight download into
-RAM and no model sharding.
+
+**Edge0-35b-a3b** — an 35B MoE LLM that runs at viable speed on portable devices in under **2.9 GiB of active memory** (1/8 of its 23 GB weight footprint), 
+via the [edge0](https://github.com/Edge0-AI/edge0) streaming inference framework.
+
+The key is streaming: experts are memory-mapped and fetched from SSD only as routed, 
+so RAM holds just the active weights. What makes that viable — instead of stalling like plain parameter offloading — 
+is a trained prerouter head that **predicts the next token's expert routing one step ahead**, hiding storage latency behind compute.
 
 > **Preview status:** this is an early preview release of the edge0
 > pipeline. The checkpoint ships as int4 quantization plus LoRA and