AI News Today | Julian Goldie Podcast
Qwable 27B Coder: Best Local Coding Model Yet? (Benchmarks, Demos & How to Run on Mac)The video demos Qwable 27B Coder, a new open-source local coding model on Hugging Face (updated end of June) built on a Qwen 3.6 27B base, showing projects made locally like a polished animated landing page and working games. It’s run on a Mac Studio (Apple M4 Max, 36GB) using Apple MLX (not available via Ollama) and is integrated into an agent operating system to generate live previews and save builds in a workspace. The presenter says Qwable tops their local leaderboards (Goldie Bench/Cody Bench comparisons) and outperforms recently tested local models like Gemma 4 12B Coder, Quifos 9B, and Onif 1.0 on the same tasks, though it runs noticeably slower than smaller models such as Quifos 9B.00:00 [https://www.youtube.com/watch?v=wfLT0vWjYVY] Meet Qwable 27B00:56 [https://www.youtube.com/watch?v=wfLT0vWjYVY&t=56s] Demos Landing Pages01:23 [https://www.youtube.com/watch?v=wfLT0vWjYVY&t=83s] Model Specs Setup02:04 [https://www.youtube.com/watch?v=wfLT0vWjYVY&t=124s] Benchmarks Versus Locals02:40 [https://www.youtube.com/watch?v=wfLT0vWjYVY&t=160s] Running On Mac03:03 [https://www.youtube.com/watch?v=wfLT0vWjYVY&t=183s] Agent OS Live Previews04:24 [https://www.youtube.com/watch?v=wfLT0vWjYVY&t=264s] Speed Tradeoffs05:00 [https://www.youtube.com/watch?v=wfLT0vWjYVY&t=300s] Real Task Comparisons05:49 [https://www.youtube.com/watch?v=wfLT0vWjYVY&t=349s] Local AI Is Accelerating06:05 [https://www.youtube.com/watch?v=wfLT0vWjYVY&t=365s] Agent OS Features Tour06:40 [https://www.youtube.com/watch?v=wfLT0vWjYVY&t=400s] Community Courses Pitch07:28 [https://www.youtube.com/watch?v=wfLT0vWjYVY&t=448s] Wrap Up Thanks
560 episodios
Comentarios
0Sé la primera persona en comentar
¡Regístrate ahora y únete a la comunidad de AI News Today | Julian Goldie Podcast!