Mistral 7B 4-bit quantization runs no problem on an 8GB M2(x.com)11 points by tosh 2 years ago | 0 comments
DeepSeek R1 671B running on 2 M2 Ultras faster than reading speed(twitter.com)36 points by thyrox 1 year ago | 11 comments
Kimi K2 1T model runs on 2 512GB M3 Ultras(twitter.com)196 points by jeudesprits 10 months ago | 98 comments
GateGPT: 56k tokens per second Transformer (KV cache) on FPGA at 80 MHz(twitter.com)27 points by laxmena 4 months ago | 8 comments
Snapdragon Oryon, faster than Apple's M2 chip at 30% less power(twitter.com)42 points by fariszr 3 years ago | 34 comments