No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by youssofal · Claude Skill · ★ 2.4k
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is MTPLX safe to install? View the security audit →
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. The model drafts several tokens ahead of itself, one batched forward pass verifies the draft, and tokens are committed through exact rejection sampling with residual correction. The output distribution is the model's own at any temperature, and decode runs at around twice the speed of plain decoding: measured 1.6x on a 16 GB M4 Mac mini and 2.24x on an M5 Max. Measured speeds Every number below was measured on a MacBook Pro M5 Max with 128 GB, fans verified at maximum, sampled at the model's own settings. Conditions and sources for every row, with the raw
| Stars | 2,379 |
| Forks | 181 |
| Language | Python |
| Category | Claude Skill |
| License | Apache-2.0 |
| Quality Score | 62.8081670329395/100 |
| Open Issues | 88 |
| Last Updated | 2026-09-19 |
| Created | 2026-05-02 |
| Platforms | claude-code, python |
| Est. Tokens | ~19k |
These tools work well together with MTPLX for enhanced workflows:
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.
Up to 4× faster LLM decoding on Apple Silicon, lossless. Native MLX port of DeepSeek's DSpark & z-lab's DFlash
Run Claude Code 100% on-device with local AI on Apple Silicon. MLX-native Anthropic-API server. 6 fighters inc
High-performance OpenAI and Anthropic compatible LLM inference server for Apple Silicon. Native MLX, continuou
Native LLM inference server for Apple Silicon. OpenAI + Anthropic API compatible. No Python. Includes MLX Core
Turn Windsurf / Devin Desktop's 100+ AI models (Claude, GPT, Gemini, DeepSeek, Kimi, GLM, SWE) into OpenAI-, A
Lemonade helps users discover and run local AI apps by serving optimized LLMs right from their own GPUs and NP
Explore other popular claude skill tools:
MTPLX is The fastest way to run Qwen 3.8 Flash Next and Qwen 3.8 27B on a Mac: 125 tok/s in OpenCode on an M5 Max. Native MTP speculative decoding on Apple Silicon, exact at any temperature. OpenAI and Anthrop. It is categorized as a Claude Skill with 2.4k GitHub stars.
MTPLX is primarily written in Python. It covers topics such as anthropic-compatible, apple-silicon, claude-code.
You can find installation instructions and usage details in the MTPLX GitHub repository at github.com/youssofal/MTPLX. The project has 2.4k stars and 181 forks, indicating an active community.
MTPLX is released under the Apache-2.0 license, making it free to use and modify according to the license terms.
The top alternatives to MTPLX on Agent Skills Hub include mlx-dspark, claude-code-local, vllm-mlx. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. 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: