| ▲ | ttoinou 5 hours ago |
| M5 Max 64GB (sweet spot) or 128GB (only 1000 USD, better to keep it for the future) more are the best quality price ratio, future proof, reliable, resellable and flexible workloads. Harder to use as a server might be the only drawback |
|
| ▲ | throwaw12 5 hours ago | parent | next [-] |
| What do you recommend for non-Mac setup? I am a Mac user, but its getting expensive, and not seeing reason to jump to the latest M5 |
| |
| ▲ | barbacoa 2 hours ago | parent | next [-] | | Try looking into Ryzen AI Max 395. AMD made a CPU/GPU soc with unified memory specifically for ai inference. Can buy mini PCs with up to 128gb ram. | | |
| ▲ | krzyk 36 minutes ago | parent | next [-] | | Isn't CUDA/nvidia the go to solution for most local models, with the rest being second class citizents? | |
| ▲ | simple10 2 hours ago | parent | prev [-] | | The Ryzen AI Max 395 128gb is super cool, but not fast for inference. Order of magnitude slower than dedicated GPU but at half the cost. You can run larger models on it but it's slow. Great for local async work. Not great for daily chat or code agent driver. | | |
| ▲ | throwa356262 an hour ago | parent [-] | | The latest NPUs are pretty fast, I think what is missing is more optimised software support. | | |
| ▲ | plagiarist 23 minutes ago | parent [-] | | The vRAM bandwidth is at least as much a problem as compute on these ones, there is a lot of data to shuffle around |
|
|
| |
| ▲ | varispeed 4 hours ago | parent | prev [-] | | Probably a comparable non-Mac setup will be Threadripper, but it will become much more expensive. My view is that actually Apple products are the cheapest on the market when it comes to performance. |
|
|
| ▲ | roger_ 5 hours ago | parent | prev [-] |
| M5 Max 128GB for $1k? |
| |
