MTPLX: The fastest way to run Qwen 3.8 Flash Next, Qwen 3.8 27B and Ternary Bonsai 2 27B on a Mac

by youssofal · Claude Skill · ★ 2.7k

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

How to install MTPLX

brew install youssofal/mtplx/mtplx

Taken from the project's README on GitHub. Check the security audit before running it.

Security audit verdict: SAFE · quality 63/100

None of the 42 rules matched — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against 42 published rules built on the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

The quality score combines nine heuristic checks of the repo and its README: completeness, clarity, specificity, examples, structure, agent readiness, step-by-step content, instruction quality and security notes. It rates how well the project explains itself to an agent, not the code.

anthropic-compatibleapple-siliconclaude-codeflash-nextinference-enginellm-inferencelocal-ailocal-llmmacosmetal

Quick Facts

Stars2,683
Forks210
LanguagePython
CategoryClaude Skill
LicenseApache-2.0
Quality Score63/100
Open Issues67
Last Updated2026-11-07
Created2026-05-02
Platformsclaude-code, python
Est. Tokens~19k

About MTPLX

The fastest way to run Qwen 3.8 on a Mac. MTPLX is a native Mac app and a command line that runs local language models on Apple Silicon with the model's own multi-token prediction (MTP) heads. It runs Qwen 3.8 Flash Next, the 125B mixture of experts, and Qwen 3.8 27B, plus Qwen 3.6, Qwen 3.5 and Gemma 4.

Compatible Skills

These tools work well together with MTPLX for enhanced workflows:

  • mlx-dspark — semantic(0.67)+complementary+shared_fw(openai)+rare_topics+same_lang+similar_pop+shared_platform (96%)
  • vllm-mlx — semantic(0.41)+complementary+shared_fw(anthropic,openai)+rare_topics+same_lang+similar_pop+shared_platform (85%)
  • mlx-omni-server — semantic(0.29)+complementary+shared_fw(anthropic,openai)+rare_topics+same_lang+similar_pop+shared_platform (81%)
  • mlx-serve — semantic(0.34)+complementary+shared_fw(anthropic,openai)+rare_topics+similar_pop+shared_platform (72%)

MTPLX alternative? Top 6 similar tools

Looking for a MTPLX alternative? If you're comparing MTPLX with other claude skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.

  • mlx-dspark by ARahim3 · ⭐ 698

    Up to 4× faster LLM decoding on Apple Silicon, lossless. Native MLX port of DeepSeek's DSpark & z-lab's DFlash

  • slotstream by carloslfu · ⭐ 652

    Run a 105 GB AI model on a Mac that can't hold it. Qwen3.8-Flash-Next 4-bit, streamed from SSD on 16–64 GB App

  • Rapid-MLX by raullenchai · ⭐ 4.1k

    Rapid-MLX is an open-source (Apache 2.0) OpenAI- and Anthropic-compatible LLM inference server for Apple Silic

  • claude-code-local by nicedreamzapp · ⭐ 3.5k

    Hit your Claude Code usage limit? Keep going free and offline on a local model. Claude Code Local runs on Appl

  • vllm-mlx by waybarrios · ⭐ 1.6k

    High-performance OpenAI and Anthropic compatible LLM inference server for Apple Silicon. Native MLX, continuou

  • mlx-serve by ddalcu · ⭐ 2.4k

    Native LLM inference server for Apple Silicon. OpenAI + Anthropic API compatible. No Python. Zig backend, Swif

More Claude Skill Tools

Explore other popular claude skill tools:

View all Claude Skill tools →

Popular Python Agent Tools

How this security grade is produced

Grades come from a rule-based scan built on the SlowMist agent-security taxonomy: 42 published rules, covering credential harvesting, data exfiltration, curl | sh installers and more. It is a first-layer scan, not a manual audit — we say so rather than overstate it.

The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.

Sources & who's responsible:

View on GitHub → Browse Claude Skill tools