Upload README.md with huggingface_hub

README.md

@@ -30,7 +30,7 @@ pipeline_tag: text-generation
 </div>
 
 
-**Edge0-8b-a1b** — an 8B MoE LLM that runs at viable speed on portable devices in under **1.0 GiB of active memory** (1/4 of its 4.2 GB weight footprint), 
+**Edge0-8b-a1b** — an 8B MoE LLM that runs at viable speed on a phone in under **1 GiB of active memory** (1/4 of its 4.2 GB weight footprint), 
 via the [edge0](https://github.com/Edge0-AI/edge0) streaming inference framework.
 
 
@@ -42,10 +42,10 @@ via the [edge0](https://github.com/Edge0-AI/edge0) streaming inference framework
 
 - **Runs in phone-class memory**: the full 4-bit checkpoint stays on
   storage and experts are streamed on demand, so only the active
-  weights are in RAM — under **1.0 GiB**, with no sharding and no
+  weights are in RAM — under **1 GiB**, with no sharding and no
   upfront download of the weights into memory.
-- **Fast enough for interactive use**: 23.9–25.3 tok/s decode on a
-  Mac mini M4 Pro; long prompts fill in at 500–1428 tok/s.
+- **Fast enough for interactive use**: 25 tok/s decode on a phone;
+  long prompts fill in at 1400 tok/s.
 - **Quality kept after quantization**: Recover-LoRA distillation keeps
   the int4 model within **2.8 points** of its fp16 base (and above it
   on MMLU-Pro).
@@ -130,7 +130,7 @@ Expert weights stream from SSD on demand and are not resident.
 - The MLX backend currently targets Apple Silicon; other backends are
   on the edge0 roadmap.
 - Long contexts grow the KV cache (≈3.3 GiB at 3.3k tokens); use
-  shorter contexts to keep peak memory at 1.0 GiB.
+  shorter contexts to keep peak memory at 1 GiB.
 
 ## Quick start