@nash_su: Mac inference speed doubled. MTPLX is an integrated solution combining MLX and MTP, specifically optimized for model inference on Apple Silicon. By using models with a custom MTP head, it can deliver doubled inference speed. I tested it with Qwen3.6-27…
Summary
MTPLX is an integrated solution combining MLX and MTP, specifically optimized for model inference speed on Apple Silicon. Tests show that Qwen3.6-27B achieves double the inference speed of LM Studio, and it also integrates fan management.
View Cached Full Text
Cached at: 05/16/26, 07:13 AM
Mac inference speed doubled 🚀
MTPLX is an integrated solution of MLX + MTP, specifically optimized for model inference on Apple Silicon. Using models with a custom MTP head, it can double the inference speed.
I’ve tested it. Qwen3.6-27B’s inference speed is double that of LMStudio. It also integrates fan management. Great 👍
Project link: https://t.co/qqkhJgpbjC
Similar Articles
MTPLX V1: The Swift App For Running & Creating MLX MTP Models (2x TPS Qwen 3.6 27B)
MTPLX V1 is a native Mac app that bundles the MTP speculative decoding engine for MLX models, offering features like model conversion via Forge, built-in chat, benchmarking, and support for smaller models. It achieves over 2x speedup with mathematical exactness.
@cevenif: For those running local LLMs on Macs, here's a tool worth watching — Rapid-MLX. It delivers 2-4x faster inference on M-series chips than Ollama, thanks to being built directly on Apple's MLX framework for more thorough utilization of the chip architecture. Key highlights: KV cache pruning plus…
Rapid-MLX is a local LLM inference tool optimized for Apple M-series chips. Built on the MLX framework, it achieves 2 to 4 times faster inference than Ollama, supports multiple models, tool calling, and an OpenAI API-compatible interface.
@nicekate8888: For the past twenty days, I've been obsessing over one thing — how to make Qwen3.6-27B run fast and well on my Mac. I started with Unsloth Q5, got 18 tok/s, and the fan was roaring. Then I switched to MLX 6bit + DFlash, hitting 22 tok/s, still not fast enough. Eventually I found MTPLX 4bit: 43 tok/s with good quality.
The user shares their experience optimizing Qwen3.6-27B inference speed on a Mac using different quantization methods (Unsloth Q5, MLX 6bit + DFlash, MTPLX 4bit), ultimately reaching 43 tok/s.
@Youssofal_: 72+ TPS on Qwen 3.6 27B on a Macbook pro M5 max. MTPLX V2 out now! The fastest way to run models on MLX.
MTPLX V2 is released, claiming 72+ tokens per second on Qwen 3.6 27B running on a Macbook Pro M5 Max via MLX.
@Youssofal_: Thank you to Kate for the comprehensive review of MTPLX. She’s tested multiple different MLX runtimes and concluded MTP…
nicekate tested multiple MLX runtimes on a Mac for running Qwen3.6-27B and concluded that MTPLX is the fastest, achieving 43 tok/s at 4bit quantization.