Professional model card

README.md

@@ -1,24 +1,24 @@
 ---
 license: gemma
 base_model: google/gemma-3-1b-it
+library_name: basert
+pipeline_tag: text-generation
 tags:
   - basert
-  - base-format
   - apple-silicon
   - quantized
 ---
 
-# gemma-3-1b-it (BaseRT `.base`)
+# gemma-3-1b-it
 
-[BaseRT](https://github.com/basecompute/baseRT) `.base` conversions of
-[`google/gemma-3-1b-it`](https://huggingface.co/google/gemma-3-1b-it) for the BaseRT Apple-Silicon (Metal)
-inference engine. Converted **directly from the bf16 source** (no
-quant-from-quant) to avoid compounding quantization error.
+[BaseRT](https://github.com/basecompute/baseRT) `.base` builds of [`google/gemma-3-1b-it`](https://huggingface.co/google/gemma-3-1b-it) for fast local inference on Apple Silicon (Metal).
 
-| File | Quant | Size |
-|------|-------|------|
-| `gemma-3-1b-it-Q4.base` | `base_q4` | 561M |
-| `gemma-3-1b-it-Q8.base` | `base_q8` | 1.0G |
+## Files
+
+| File | Precision | Size |
+|------|-----------|------|
+| `gemma-3-1b-it-Q4.base` | 4-bit | 580 MB |
+| `gemma-3-1b-it-Q8.base` | 8-bit | 1.0 GB |
 
 ## Usage
 
@@ -28,4 +28,4 @@ basert pull basecompute/gemma-3-1b-it
 basert chat basecompute/gemma-3-1b-it
 ```
 
-Context: 32k · License inherited from the base model.
+Released under the gemma license, inherited from the base model.