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

README.md

@@ -74,77 +74,53 @@ widget:
     content: A train leaves station A at 60 mph and another leaves station B, 180
       miles away, at 40 mph toward each other. When do they meet?
 ---
+> **Run this on your Mac with [Outlier](https://outlier.host/?utm_source=hf&utm_medium=modelcard&utm_campaign=deepseek_r1_distill_qwen_32b_mlx_4bit)** — a one-click app that loads MLX models locally. macOS arm64, free download.
 
-# DeepSeek-R1-Distill-Qwen-32B — MLX 4-bit
+# DeepSeek-R1-Distill-Qwen-32B (MLX 4-bit)
 
-4-bit MLX conversion of [DeepSeek-R1-Distill-Qwen-32B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-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 [`deepseek-ai/DeepSeek-R1-Distill-Qwen-32B`](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B), repackaged for Apple Silicon. Original weights, original license — see frontmatter above. This repo only changes the on-disk format (safetensors, MLX 4-bit, `chat_template.jinja`, tokenizer).
 
-## Quick facts
+## About this conversion
 
-- **Upstream base:** [DeepSeek-R1-Distill-Qwen-32B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B)
-- **Format:** MLX 4-bit (`mlx_lm.convert --q-bits 4 --q-group-size 64`)
-- **License:** `mit`
-- **Use case:** reasoning
-- **Runtime:** mlx-lm, LM Studio, Jan, Outlier desktop app
-- **Publisher:** Outlier-Ai (solo, Mac-native AI platform)
+- **Format:** MLX 4-bit safetensors (group size 64, symmetric)
+- **Tooling:** `mlx-lm` 0.31.x compatible
+- **Files:** `model.safetensors` shards · `config.json` · tokenizer · `chat_template.jinja`
+- **License:** inherits from the upstream base model — see YAML `license` field
 
-## Quickstart (mlx-lm)
+### Load directly with `mlx-lm`
 
 ```bash
-pip install -U mlx-lm
+pip install mlx-lm
 python -m mlx_lm.generate \
   --model Outlier-Ai/DeepSeek-R1-Distill-Qwen-32B-MLX-4bit \
-  --prompt "Write a haiku about compilers." \
+  --prompt "Hello, world." \
   --max-tokens 256
 ```
 
-## Quickstart (LM Studio)
+Or in Python:
 
-Search for `Outlier-Ai/DeepSeek-R1-Distill-Qwen-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 `reasoning`.
-
-## Why this repo exists
-
-This is a canonically-named twin of [Outlier-Ai/Outlier-R1-Distill-32B-MLX-4bit](https://huggingface.co/Outlier-Ai/Outlier-R1-Distill-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 "deepseek-r1-distill-qwen-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: [DeepSeek-R1-Distill-Qwen-32B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B)
-- Date produced: 2026-04-19 (Day 19)
-- Conversion factory: Outlier MEGA-INFINITE phase3
+```python
+from mlx_lm import load, generate
+model, tokenizer = load("Outlier-Ai/DeepSeek-R1-Distill-Qwen-32B-MLX-4bit")
+print(generate(model, tokenizer, prompt="Hello, world.", max_tokens=256))
+```
 
-## Related
+## What is Outlier?
 
-- **Branded twin (same weights):** [Outlier-Ai/Outlier-R1-Distill-32B-MLX-4bit](https://huggingface.co/Outlier-Ai/Outlier-R1-Distill-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)
+Outlier is a free macOS app that runs language models on your Mac, fully offline. Pick a model from a tier picker, click download, and chat — no API keys, no cloud round-trips, no usage caps. It ships with its own curated tier of MLX-4bit models and can also load any compatible MLX conversion (including this one) via the model picker.
 
-## Collections
+➡ Download Outlier (free, Apple Silicon): **[outlier.host](https://outlier.host/?utm_source=hf&utm_medium=modelcard&utm_campaign=deepseek_r1_distill_qwen_32b_mlx_4bit)**
 
-- **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)
+For benchmark numbers (MMLU, HumanEval, tok/s on M-series Macs) with full provenance, see [outlier.host/benchmarks](https://outlier.host/benchmarks?utm_source=hf&utm_medium=modelcard&utm_campaign=deepseek_r1_distill_qwen_32b_mlx_4bit).
 
-## Attribution
+## Other Outlier conversions
 
-Base model by the upstream author (see [DeepSeek-R1-Distill-Qwen-32B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B)). Outlier contributes
-the MLX 4-bit conversion and desktop-app packaging. Capability credit for the base
-belongs entirely to upstream.
+- [DeepSeek-R1-Distill-Qwen-7B (MLX 4-bit) — MLX 4-bit conversion (1,932 downloads)](https://huggingface.co/Outlier-Ai/DeepSeek-R1-Distill-Qwen-7B-MLX-4bit)
+- [DeepSeek-R1-Distill-Llama-8B (MLX 4-bit) — MLX 4-bit conversion (1,148 downloads)](https://huggingface.co/Outlier-Ai/DeepSeek-R1-Distill-Llama-8B-MLX-4bit)
+- [DeepSeek-R1-Distill-Qwen-14B (MLX 4-bit) — MLX 4-bit conversion (1,087 downloads)](https://huggingface.co/Outlier-Ai/DeepSeek-R1-Distill-Qwen-14B-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: `mit`. Respect the terms of
-[DeepSeek-R1-Distill-Qwen-32B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B) when using this conversion.
+This conversion preserves the upstream license declared in the frontmatter (`mit`). Refer to the upstream base model card for the canonical license text and any usage restrictions.