← Back to context Comment by reactordev 1 day ago I run local models on Mac studios and they are more than capable. Don’t spread fud. 3 comments reactordev Reply bottlepalm 1 day ago You're spreading fud. There's nothing you can run locally that's on par with the speed/intelligence of a SOTA model. 3836293648 1 day ago You may be correct about the level of models you can actually run on consumer hardware, but it's not fud and you're being needlessly aggressive here. CamperBob2 19 hours ago Incorrect as of a couple of days ago, when Qwen 3.5 came out. It's a GPT 5-class model that you can run at full strength on a small DGX Spark or Mac cluster, and it still works pretty well after quantization.
bottlepalm 1 day ago You're spreading fud. There's nothing you can run locally that's on par with the speed/intelligence of a SOTA model. 3836293648 1 day ago You may be correct about the level of models you can actually run on consumer hardware, but it's not fud and you're being needlessly aggressive here. CamperBob2 19 hours ago Incorrect as of a couple of days ago, when Qwen 3.5 came out. It's a GPT 5-class model that you can run at full strength on a small DGX Spark or Mac cluster, and it still works pretty well after quantization.
3836293648 1 day ago You may be correct about the level of models you can actually run on consumer hardware, but it's not fud and you're being needlessly aggressive here.
CamperBob2 19 hours ago Incorrect as of a couple of days ago, when Qwen 3.5 came out. It's a GPT 5-class model that you can run at full strength on a small DGX Spark or Mac cluster, and it still works pretty well after quantization.
You're spreading fud. There's nothing you can run locally that's on par with the speed/intelligence of a SOTA model.
You may be correct about the level of models you can actually run on consumer hardware, but it's not fud and you're being needlessly aggressive here.
Incorrect as of a couple of days ago, when Qwen 3.5 came out. It's a GPT 5-class model that you can run at full strength on a small DGX Spark or Mac cluster, and it still works pretty well after quantization.