--- title: "I Ran QWEN 3.6 vs Gemma 4 Locally on M5 Max — The 6X Gap Is Embarrassing" url: https://daily.dev/posts/i-ran-qwen-3-6-vs-gemma-4-locally-on-m5-max-the-6x-gap-is-embarrassing-ydewka0ds source_url: https://www.youtube.com/watch?v=fqaE-Hfwwe8 type: video:youtube source: "Execute Automation" published: 2026-05-31T07:48:16.386Z updated: 2026-06-18T02:15:08.136Z tags: ["gemma", "lm-studio", "local-ai", "qwen"] reading_time: 15 upvotes: 0 comments: 0 language: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # I Ran QWEN 3.6 vs Gemma 4 Locally on M5 Max — The 6X Gap Is Embarrassing **[Execute Automation](https://daily.dev/sources/executeautomation)** · 15 min read · 0 upvotes · 0 comments ## Summary A hands-on comparison of Qwen 3.6 (35B MoE) vs Gemma 4 (31B) running locally on an Apple M5 Max with 128GB RAM using LM Studio. Tests include SVG image generation and a browser-based snake game. Qwen 3.6 consistently outperforms Gemma 4 in inference speed (~110 tokens/sec vs ~16 tokens/sec), thinking time (under 1 second vs 25-105 seconds), and output quality. Both models are vision-capable, but Qwen 3.6 produced more complete and functional code outputs. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Similar posts on daily.dev - [I ran Gemma 4 and Qwen 3.5 for the same local tasks, and one pulled miles ahead](https://daily.dev/posts/i-ran-gemma-4-and-qwen-3-5-for-the-same-local-tasks-and-one-pulled-miles-ahead-ukuc7wocd) · XDA Developers · 0 upvotes · 0 comments - [I ran Gemma, Llama, and Qwen on my phone, and only one of them is worth the storage](https://daily.dev/posts/i-ran-gemma-llama-and-qwen-on-my-phone-and-only-one-of-them-is-worth-the-storage-wimnfxtiv) · XDA Developers · 0 upvotes · 0 comments --- Tags: [#gemma](https://daily.dev/tags/gemma), [#lm-studio](https://daily.dev/tags/lm-studio), [#local-ai](https://daily.dev/tags/local-ai), [#qwen](https://daily.dev/tags/qwen) [View this post on daily.dev](https://daily.dev/posts/i-ran-qwen-3-6-vs-gemma-4-locally-on-m5-max-the-6x-gap-is-embarrassing-ydewka0ds)