---
type: xpost
source_url: https://x.com/jun_song/status/2071625328083227118
author: "@jun_song"
date: 2026-06-29
posted_by: Pit Weber (@PWeber)
topic: "Tips & Tricks (Topic 27)"
tags: [xpost, mlx, moe, local-ai, apple-silicon, mac, dense-vs-moe, deepseek, minimax, qwen, info-gap, knowledge-cutoff]
---

# Jun Song: MLX is optimized for MoE, not dense models — the local AI info gap

**Source:** [X-Post by @jun_song](https://x.com/jun_song/status/2071625328083227118)
**Posted:** 2026-06-29
**Shared by:** Pit Weber in OME-Gruppe, Topic "Tips & Tricks" (Topic 27)

## Post Content

Jun Song (@jun_song) explains the critical info gap in local AI deployment on Apple Silicon:

> Most people think Qwen3.6 27B is the best local model, so they run it on a 128GB Mac. But MLX is actually optimized for MoE (Mixture of Experts), not dense models — it fully leverages Apple's massive unified RAM. Running a 27B dense model is painfully slow on Mac. Running the dq (dequantized) version of Minimax-M3.0 or Deepseek-v4-Flash is a much smoother experience.
>
> The catch: No frontier AI can tell you this. You can't search for it, and knowledge cutoffs mean they don't have the latest facts.
>
> This info gap is why people keep saying local AI is years behind.
>
> Recommendation: Look at the latest info on experts' X accounts and follow what they do.

### Context

This post is a reply to a quoted post by @firstadopter (Tae Kim) who was complaining about running the latest Qwen on a 128GB Mac being too slow and hot, concluding that viable local LLMs are years away.

## Key Technical Points

| Point | Detail |
|-------|--------|
| **MLX optimization target** | MoE (Mixture of Experts), not dense models |
| **Apple Silicon advantage** | Massive unified RAM is ideal for MoE's sparse activation pattern |
| **Dense model penalty** | 27B dense model (e.g., Qwen3.6 27B) is "painfully slow" on Mac |
| **Recommended MoE models** | Minimax-M3.0 (dq), Deepseek-v4-Flash (dq) — dequantized versions |
| **Info gap cause** | Frontier AI models have knowledge cutoffs; can't search for cutting-edge local AI optimization info |
| **Recommendation** | Follow expert X accounts for latest local AI deployment knowledge |

## Engagement

- 954 likes
- 60 reposts
- 51 replies
- 862 bookmarks
- ~89K views

## Relevance to Our Setup

1. **Direct model overlap:** We use GLM 5.2 Cloud as primary, with **minimax-m3** and **deepseek-v4-flash** as fallbacks — the exact models Jun Song recommends for local MLX execution
2. **Validates our model choices from a different angle:** Not just cost routing (DeRonin's angle) or macro-thesis (TheProphet's angle), but **local MLX hardware optimization** — MoE models leverage Apple Silicon's unified memory architecture better than dense models
3. **Info gap thesis:** Jun Song's point that "no frontier AI can tell you this" is directly relevant to the knowledge base curation mission — this is exactly why we wikify expert knowledge from X posts
4. **Cloud-Exit connection:** Practical guide for Mac users on which models to run locally — complements the Cloud-Exit hardware thesis
5. **Dense vs. MoE:** The architectural distinction matters for deployment decisions, not just academic taxonomy

## Related Wiki Pages

- `wiki/concepts/hardware/cloud-exit-and-local-superiority.md` — Cloud-Exit thesis, local MoE on Mac
- `wiki/concepts/llm/chinese-model-cost-routing.md` — DeRonin's cost routing (same models, different angle)
- `wiki/concepts/llm/llm-model-catalog.md` — Consolidated model catalog with local deployment info
- `wiki/concepts/llm/ai-intelligence-commoditization-thesis.md` — Macro context for model accessibility
- `wiki/architecture/model-routing.md` — Our routing architecture using these models