| ▲ | lostmsu 5 hours ago |
| Will 2026 M5 MacBook come with 390+GB of RAM? |
|
| ▲ | alex43578 5 hours ago | parent | next [-] |
| Quants will push it below 256GB without completely lobotomizing it. |
| |
| ▲ | lostmsu 2 hours ago | parent [-] | | > without completely lobotomizing it The question in case of quants is: will they lobotomize it beyond the point where it would be better to switch to a smaller model like GPT-OSS 120B that comes prequantized to ~60GB. |
|
|
| ▲ | bertili 5 hours ago | parent | prev | next [-] |
| Most certainly not, but the Unsloth MLX fits 256GB. |
| |
| ▲ | embedding-shape 5 hours ago | parent [-] | | Curious what the prefilled and token generation speed is. Apple hardware already seem embarrassingly slow for the prefill step, and OK with the token generation, but that's with way smaller models (1/4 size), so at this size? Might fit, but guessing it might be all but usable sadly. | | |
| ▲ | regularfry 3 hours ago | parent [-] | | They're claiming 20+tps inference on a macbook with the unsloth quant. | | |
| ▲ | embedding-shape 9 minutes ago | parent [-] | | Yeah, I'm guessing the Mac users still aren't very fond of sharing the time the prefill takes, still. They usually only share the tok/s output, never the input. |
|
|
|
|
| ▲ | margorczynski 3 hours ago | parent | prev [-] |
| My hope is the Chinese will also soon release their own GPU for a reasonable price. |
