@remilouf: Following @julien_c’s tweet I bought a MacBook Pro with 128B unified memory, and started running Qwen3.6 as my daily dr…
Summary
The author shares their experience running the Qwen3.6 model on a MacBook Pro with 128GB of unified memory, praising Apple's hardware efficiency for local AI inference.
View Cached Full Text
Cached at: 05/10/26, 04:27 PM
Following @julien_c’s tweet I bought a MacBook Pro with 128B unified memory, and started running Qwen3.6 as my daily driver. It’s baffling.
Apple outsmarted everyone in this industry.
Similar Articles
@Oluwaphilemon1: Qwen3.8-27B is running locally on an M1 MacBook with just 16GB of unified memory. No cloud API. No external GPU. Just a…
Qwen3.8-27B is shown running locally on an M1 MacBook with 16GB unified memory using UD-Q2_K_XL quantization and full Metal offload, achieving ~4 tokens/sec generation (~5.5 with speculative decoding) — demonstrating that large open-weight models can run on hardware many people already own.
QWEN3.6-27B-MLX-8bit (29.5GIG) Is Excellent
A user shares their experience switching to the QWEN3.6-27B-MLX-8bit model for local AI tasks, finding it performs comparably to larger models while saving significant RAM on a Mac Studio, improving workflow stability.
Qwen3.8-27B at 144 tok/s on an M5 Max MacBook Pro
Inco Splash is an open-source inference engine optimized for Apple silicon, offering significant speed improvements for running AI models like Qwen3.8-27B on M-series MacBooks.
Run Qwen3.8 27B locally: real numbers from my Mac Studio
The article provides real-world performance benchmarks for running the Qwen3.8 27B AI model locally on a Mac Studio, comparing it to its predecessor and discussing hardware requirements and quantization effects.
Maxing out 64GB of RAM - Qwen3.5 122B A10B at UD-Q2_K_XL w/ MTP fully replaced Qwen3 Next 80B at UD-Q4_K_XL for me
A user compares running quantized Qwen3 Next 80B and Qwen3.5 122B on a 64GB RAM system, noting the trade-offs in speed, quality, and memory usage for local LLM inference.