Card: verified one-command usage, measured Performance table (backends gated on real generation), accuracy note

README.md

@@ -37,7 +37,43 @@ tiny, fast on-device VLM — give it an image and a question, get a grounded ans
 | **Image input** | resized to 448×448 (ImageNet normalization baked into the vision encoder) |
 | **Base model** | OpenGVLab/InternVL3-1B |
 
-## Quality
+## How to use
+
+**1. Install the runtime**
+
+```bash
+pip install litert-lm
+```
+
+**2. Run it in one command** — this downloads the bundle, encodes your image and answers:
+
+```bash
+litert-lm run --from-huggingface-repo litert-community/InternVL3-1B InternVL3-1B.litertlm \
+  --attachment photo.jpg \
+  --prompt "Describe this image in one sentence."
+```
+
+On the COCO sample image `huggingface/documentation-images/coco_sample.png` (two tabby cats on a pink blanket, remote controls beside them) this prints:
+
+```
+The image shows two cats lying on a pink bed with two remote controls.
+```
+
+Drop `--prompt` for an interactive chat, and pass `--attachment` more than once for several images. `litert-lm serve` exposes the same bundle as a local OpenAI-compatible API. The same file runs on macOS, Linux and Windows.
+
+## Performance
+
+`litert-lm benchmark` (litert-lm 0.15.0) on an Apple M4 Max, `-p 256 -d 256 --runs 3` (the tool averages three iterations), max-num-tokens 4096, warm-up run discarded, otherwise idle machine. These figures cover the text path; the vision encoder runs once per image and is not included.
+
+| Device | Backend | Prefill (256) | Decode | TTFT |
+|---|---|---|---|---|
+| Apple M4 Max (macOS) | CPU | 454 tok/s | 94.0 tok/s | 0.62 s |
+
+Every desktop backend listed above was checked by actually generating a caption on it, not just by reading the benchmark tool's output.
+
+**The macOS GPU backend is not usable for this bundle on litert-lm 0.15.0.** Asked to describe an image with `--backend gpu`, it returns a run of `!` characters instead of a caption. `litert-lm benchmark` still reports GPU numbers for it — 5,583 tok/s prefill and 342 tok/s decode — but they measure a path that produces no usable text, so no GPU row is quoted here. Use the CPU backend on the desktop. This is a desktop-runtime observation and says nothing about the iPhone or Android GPU paths described elsewhere on this card.
+
+### Accuracy note
 
 Output is coherent and image-grounded (CPU-verified; the vision tower converts bit-faithfully to the
 reference, float CPU-parity corr ≈ 1.0). On-device behavior mirrors the larger InternVL3-2B build