Pedro Cuenca
@pcuenq
ML Engineer at đ¤ Hugging Face | Co-founder at LateNiteSoft (Camera+). I love AI and photography.
1.1K Following 7.7K Followers
Super happy to welcome @jundotkim, oMLX creator, to Hugging Face! đĨŗ
We are invested in Local AI and support MLX since @awnihannun and @angeloskath released it in Christmas 2023.
oMLX gets stability and speed. It remains a community project led by Jun.
Show more
tokenizers v1 (Rust): 3 to 30 times faster, opt-out tokenization training crate, lots of clever algorithms and optimizations, extensive benchmarks.
Coming soon to transformers.
Show more
My data point: working on two projects in parallel with Pi + llama.cpp + Qwen-3.6-35B-A3B (I prefer the MoE đ)
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".
Show more
Kimi K2.6 was released 1h ago, and it looks amazing!
Here it's running with MLX (mlx-vlm) on two M3 Ultras (full 1T param VLM) đĨ
đ Every model added to transformers has to be available on Apple Silicon đ at once. We built a Skill and test harness for mlx-lm to get us closer đĨ
It's designed to help contributors AND support reviewers.
Read on to see what we did and why it matters.
Show more
