๊ฐ€์ž… ํ›„ ์ดˆ๋Œ€ ๋งํฌ๋ฅผ ๊ณต์œ ํ•˜๋ฉด ๋™์˜์ƒ ์žฌ์ƒ ๋ฐ ์ดˆ๋Œ€ ๋ณด์ƒ์„ ๋ฐ›์„ ์ˆ˜ ์žˆ์Šต๋‹ˆ๋‹ค.

Pedro Cuenca
@pcuenq
ML Engineer at ๐Ÿค— Hugging Face | Co-founder at LateNiteSoft (Camera+). I love AI and photography.
๊ฐ€์ž… May 2019
1K ํŒ”๋กœ์ž‰ ์ค‘    7.3K ํŒฌ
My data point: working on two projects in parallel with Pi + llama.cpp + Qwen-3.6-35B-A3B (I prefer the MoE ๐Ÿ™ˆ) This works on my M1 Max (64 GB), which I bought 4.5 years ago. "Works" as in "you can get work done", not just "runs for a demo".
๋” ๋ณด๊ธฐ