docs(card): SEO + cross-link refresh (HF-DISCOVERABILITY-001)

README.md

@@ -94,72 +94,50 @@ model-index:
       value: 0.6951
       verified: false
 ---
+> **Part of the [Outlier](https://outlier.host/?utm_source=hf&utm_medium=modelcard&utm_campaign=outlier_lite_9b_mlx_4bit) shipping lineup.** Outlier is a free macOS app that runs this model locally, with one click. Apple Silicon only.
 
-# Outlier Lite 9B (MLX-4bit)
+# Outlier Lite 9B (MLX 4-bit)
 
-> **53.4 tok/s on M1 Ultra. MMLU 0.7846 (+2.22 σ). Balanced everyday AI for 12+ GB Macs.**
+The mid-tier shipping model. 9B dense, text-only, MLX 4-bit. Recommended for 12 GB+ Macs that want stronger reasoning than Nano without paying the latency cost of a 27B-class model.
 
-**Outlier Lite** is a text-only 4-bit MLX build of [Qwen3.5-9B](https://huggingface.co/Qwen/Qwen3.5-9B) for Apple Silicon. The balanced tier in the [Outlier](https://outlier.host) lineup — fast, capable, fits on MacBook Pro 16 GB.
+## Try it in Outlier
 
----
-
-## At a glance
-
-| Property | Value |
-|---|---|
-| Architecture | Qwen3.5, hybrid linear:full attention 3:1 |
-| Parameters | 9B |
-| Quantization | MLX 4-bit |
-| Disk size | **5.04 GB** (vision tower stripped) |
-| Min RAM | **12 GB** unified memory |
-| Speed | **53.4 tok/s** (M1 Ultra 64 GB) |
-| Context (default) | 32K (native: 256K) |
-| Thinking mode | ✅ |
-| License | Apache 2.0 |
-
----
-
-## Verified benchmarks
+The simplest way to use this model is through the Outlier app — open the tier picker, select **Outlier Lite**, click download, and chat. No setup, no Python, no MLX install, no token quotas.
 
-| Task | Metric | n | stderr | Date |
-|---|---|---|---|---|
-| MMLU (5-shot) | **0.7846** ± 0.0035 | 14,042 (full test set) | 0.003498 | 2026-04-30 |
-| HumanEval pass@1 | **0.6951** ± 0.0361 | 164 | 0.036058 | 2026-04-30 |
+➡ **[Download Outlier — outlier.host](https://outlier.host/?utm_source=hf&utm_medium=modelcard&utm_campaign=outlier_lite_9b_mlx_4bit)**
 
-MMLU: **+1.10 pp / 2.22 σ above base** — clears the strict 2σ bar. One of the most accurately benchmarked 9B models on HuggingFace.
+A screenshot of the tier picker is at [outlier.host/screenshots/tier-picker.png](https://outlier.host/screenshots/tier-picker.png?utm_source=hf&utm_medium=modelcard&utm_campaign=outlier_lite_9b_mlx_4bit).
 
----
+## Load this directly (power users)
 
-## Quick start
+If you want the raw MLX-4bit weights without the app:
 
 ```bash
 pip install mlx-lm
-mlx_lm.generate --model Outlier-Ai/Outlier-Lite-9B-MLX-4bit \
-  --prompt "Summarize the key ideas in transformers architecture." \
-  --max-tokens 256
+python -m mlx_lm.generate \
+  --model Outlier-Ai/Outlier-Lite-9B-MLX-4bit \
+  --prompt "Write a quicksort in Python." \
+  --max-tokens 512
 ```
 
 ```python
-from mlx_lm import load, stream_generate
-
+from mlx_lm import load, generate
 model, tokenizer = load("Outlier-Ai/Outlier-Lite-9B-MLX-4bit")
-for chunk in stream_generate(model, tokenizer, "What is Apple Silicon?", max_tokens=128):
-    print(chunk.text, end="", flush=True)
+print(generate(model, tokenizer, prompt="Hello", max_tokens=256))
 ```
 
----
+## Verified benchmarks
+
+For σ-qualified MMLU, HumanEval, and Mac inference-speed numbers — with full provenance (source file, command, n, stderr, date) — see **[outlier.host/benchmarks](https://outlier.host/benchmarks?utm_source=hf&utm_medium=modelcard&utm_campaign=outlier_lite_9b_mlx_4bit)**.
 
-## Outlier lineup
+## Other Outlier shipping tiers
 
-| Tier | Params | Speed | Min RAM |
-|---|---|---|---|
-| [Nano](https://hf.co/Outlier-Ai/Outlier-Nano-4B-MLX-4bit) | 4B | 71.7 tok/s | 6 GB |
-| **Lite** ← you are here | 9B | **53.4 tok/s** | 12 GB |
-| [Quick](https://hf.co/Outlier-Ai/Outlier-Quick-26B-MLX-4bit) | 26B MoE | 14.6 tok/s | 16 GB |
-| [Core](https://hf.co/Outlier-Ai/Outlier-Core-27B-MLX-4bit) | 27B | 20.7 tok/s | 24 GB |
-| [Code](https://hf.co/Outlier-Ai/Outlier-Code-27B-MLX-4bit) | 27B | 20.7 tok/s | 24 GB |
-| [Vision](https://hf.co/Outlier-Ai/Outlier-Vision-35B-A3B-MLX-4bit) | 35B MoE | ~61 tok/s | 24 GB |
+- [Outlier Nano 4B (entry tier, ~3 GB)](https://huggingface.co/Outlier-Ai/Outlier-Nano-4B-MLX-4bit)
+- [Outlier Quick 26B-A4B MoE (~16 GB)](https://huggingface.co/Outlier-Ai/Outlier-Quick-26B-MLX-4bit)
+- [Outlier Core 27B (default, ~16 GB)](https://huggingface.co/Outlier-Ai/Outlier-Core-27B-MLX-4bit)
+- [Outlier Code 27B (code-tuned, ~16 GB)](https://huggingface.co/Outlier-Ai/Outlier-Code-27B-MLX-4bit)
+- [Outlier Vision 35B-A3B (multimodal, ~20 GB)](https://huggingface.co/Outlier-Ai/Outlier-Vision-35B-A3B-MLX-4bit)
 
 ## License
 
-Apache 2.0 (inherited from Qwen3.5-9B).
+Apache 2.0 (inherits from upstream base model). Conversion artifact only — the underlying weights are governed by the base model's license.