Item — HN Reader

- "2 MacBooks is all you need. Llama 3.1 405B running distributed across 2 MacBooks using @exolabs_ home AI cluster" https://x.com/AIatMeta/status/1834633042339741961

- "Running Qwen 2.5 Math 72B distributed across 2 MacBooks. Uses @exolabs_ with the MLX backend." https://x.com/ac_crypto/status/1836558930585034961

1 comments

I experimented with both Exo and llama.cpp in RPC-server mode this week. Using an M3 Max and an M1 Ultra in Exo specifically I was able to get around 13 tok/s on DeepSeek 2.5 236B (using MLX and a 4 bit quant with a very small test prompt - so maybe 140 gigs total of model+cache). It definitely took some trial and error but the Exo community folks were super helpful/responsive with debugging/advice.