alt Hacker NewsI bought a 128GB M4 Max Mac Studio a while back, and for a while I thought like I had done really well to buy it when I did.
The problem I'm having now is that no models are targeting RAM of that size. Everything is either much smaller, targeting laptops, or much larger, targeting hardware well out of reach of enthusiasts.
Please, AI people, start making models targeting 128GB machines again. The last interesting one was Qwen 3.5 122B.
Replies
Great news. Qwen 3.8 Flash Next (125B A6B) is coming out tomorrow. 4 or 6-bit should run nicely on 128GB.
Should bench better than Opus 4.7.
It's not exactly straight out of one of the labs -- it's heavily quantized -- but have a look at [1].
Well the upside is that you can run a laptop-sized model and still have enough memory left over to run a couple of Electron apps.
If I had 128GB unified RAM I'd try hf.co/unsloth/Qwen3.8-27B-GGUF:BF16 which needs 55GB for just the weights.
Something like this would give you three concurrent sessions, each with 240k token context: