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

README.md

@@ -77,77 +77,33 @@ widget:
     content: Summarize the difference between 4-bit and 8-bit quantization in two
       short paragraphs.
 ---
+> **Run this on your Mac with [Outlier](https://outlier.host/?utm_source=hf&utm_medium=modelcard&utm_campaign=qwen3_32b_mlx_4bit)** — a free macOS app for local MLX inference.
 
-# Qwen3-32B — MLX 4-bit
+# Qwen3-32B (MLX 4-bit)
 
-4-bit MLX conversion of [Qwen3-32B](https://huggingface.co/Qwen/Qwen3-32B) for Apple Silicon. Runs natively on
-M1, M2, M3, and M4 Macs via `mlx_lm`. Faithful port of the upstream weights — no
-fine-tuning, no merge.
+MLX 4-bit conversion of [`Qwen/Qwen3-32B`](https://huggingface.co/Qwen/Qwen3-32B). License and base-model fields inherit from the original — see YAML frontmatter above.
 
-## Quick facts
-
-- **Upstream base:** [Qwen3-32B](https://huggingface.co/Qwen/Qwen3-32B)
-- **Format:** MLX 4-bit (`mlx_lm.convert --q-bits 4 --q-group-size 64`)
-- **License:** `apache-2.0`
-- **Use case:** chat
-- **Runtime:** mlx-lm, LM Studio, Jan, Outlier desktop app
-- **Publisher:** Outlier-Ai (solo, Mac-native AI platform)
-
-## Quickstart (mlx-lm)
+## Load with mlx-lm
 
 ```bash
-pip install -U mlx-lm
-python -m mlx_lm.generate \
-  --model Outlier-Ai/Qwen3-32B-MLX-4bit \
-  --prompt "Write a haiku about compilers." \
-  --max-tokens 256
+pip install mlx-lm
+python -m mlx_lm.generate --model Outlier-Ai/Qwen3-32B-MLX-4bit --prompt "Hello" --max-tokens 256
 ```
 
-## Quickstart (LM Studio)
-
-Search for `Outlier-Ai/Qwen3-32B-MLX-4bit`, then Load and chat.
-
-## Quickstart (Outlier desktop app)
-
-One-click install from [outlier.host](https://outlier.host). Listed in the library
-picker under `chat`.
-
-## Why this repo exists
-
-This is a canonically-named twin of [Outlier-Ai/Outlier-Qwen3-32B-MLX-4bit](https://huggingface.co/Outlier-Ai/Outlier-Qwen3-32B-MLX-4bit).
-Same weights, same quant, different name. The branded repo carries the Outlier
-identity; this one carries the upstream identity so it's findable via searches
-like "qwen3-32b 4bit mlx". Use whichever path you came across — both
-point to the same files.
-
-## Provenance
-
-- Converted via `mlx_lm.convert --q-bits 4 --q-group-size 64`
-- Source: [Qwen3-32B](https://huggingface.co/Qwen/Qwen3-32B)
-- Date produced: 2026-04-19 (Day 19)
-- Conversion factory: Outlier MEGA-INFINITE phase3
-
-## Related
-
-- **Branded twin (same weights):** [Outlier-Ai/Outlier-Qwen3-32B-MLX-4bit](https://huggingface.co/Outlier-Ai/Outlier-Qwen3-32B-MLX-4bit)
-- **Outlier org on HuggingFace:** [Outlier-Ai](https://huggingface.co/Outlier-Ai)
-- **Desktop app:** [outlier.host](https://outlier.host)
-- **Founders lifetime ($200, 500-seat cap):** [buy.polar.sh](https://buy.polar.sh/polar_cl_mJfYZsEpEMDcYrgxzvTdnahSeSQNq1UYLqV0l08CUhW)
-- **Discord:** [discord.gg/Hapennmdn9](https://discord.gg/Hapennmdn9)
+## What is Outlier?
 
-## Collections
+A free macOS app that runs MLX models locally — no cloud, no API keys, no usage caps.
 
-- **Outlier for Apple Silicon (MLX):** [huggingface.co/collections/Outlier-Ai/outlier-consumer-edition-69e2fb4a0df119ea1747275e](https://huggingface.co/collections/Outlier-Ai/outlier-consumer-edition-69e2fb4a0df119ea1747275e)
-- **Outlier Research MoE:** [huggingface.co/collections/Outlier-Ai/outlier-research-69e2fb3a71984614b3c7a279](https://huggingface.co/collections/Outlier-Ai/outlier-research-69e2fb3a71984614b3c7a279)
-- **Outlier Server V3.2:** [huggingface.co/collections/Outlier-Ai/outlier-server-v32-69e2fb4b71984614b3c7a4a3](https://huggingface.co/collections/Outlier-Ai/outlier-server-v32-69e2fb4b71984614b3c7a4a3)
+➡ **[outlier.host](https://outlier.host/?utm_source=hf&utm_medium=modelcard&utm_campaign=qwen3_32b_mlx_4bit)**
 
-## Attribution
+## Other Outlier conversions
 
-Base model by the upstream author (see [Qwen3-32B](https://huggingface.co/Qwen/Qwen3-32B)). Outlier contributes
-the MLX 4-bit conversion and desktop-app packaging. Capability credit for the base
-belongs entirely to upstream.
+- [Qwen3-Coder-30B-A3B-Instruct (MLX 4-bit) — MLX 4-bit conversion (1,598 downloads)](https://huggingface.co/Outlier-Ai/Qwen3-Coder-30B-A3B-Instruct-MLX-4bit)
+- [Qwen3-14B (MLX 4-bit) — MLX 4-bit conversion (466 downloads)](https://huggingface.co/Outlier-Ai/Qwen3-14B-MLX-4bit)
+- [Qwen3-8B (MLX 4-bit) — MLX 4-bit conversion (107 downloads)](https://huggingface.co/Outlier-Ai/Qwen3-8B-MLX-4bit)
+- [Outlier-Core-27B (MLX 4-bit) — MLX 4-bit conversion (55 downloads)](https://huggingface.co/Outlier-Ai/Outlier-Core-27B-MLX-4bit)
+- [Outlier-Nano-4B (MLX 4-bit) — MLX 4-bit conversion (67 downloads)](https://huggingface.co/Outlier-Ai/Outlier-Nano-4B-MLX-4bit)
 
 ## License
 
-Redistributed under the upstream license: `apache-2.0`. Respect the terms of
-[Qwen3-32B](https://huggingface.co/Qwen/Qwen3-32B) when using this conversion.
+Inherits from upstream (`apache-2.0`). See base model card.