17,000 tokens per second!! Read that again!
LLM is hard-wired directly into silicon. no HBM, no liquid cooling, just raw specialized hardware. 10x faster and 20x cheaper than a B200.
the "waiting for the LLM to think" era is dead. Code generates at the speed of human thought.
Transition from brute-force GPU clusters to actual AI appliances.
https://t.co/Bf6DH7Q6Uf
MLX MiniMax 2.5 running LOCALLY on a single M3 Ultra 512GB! Writing a poem on LLMs at 6bit quantization! 🔥
Let's start some coding, context and distributed tests!
Generation: 40.2 tokens-per-sec
Peak memory: 186 GB
This iconic photograph is still considered one of the most-terrifying space photographs to date. Astronaut Bruce McCandless II became the first human being to do a spacewalk without a safety tether linked to a spacecraft. In 1984, he floated completely untethered in space with nothing but his Manned Maneuvering Unit keeping him alive.
One of the characteristic surface hydrothermal features of the Puga Valley in Ladakh, India, are these carbonate deposits and mounds along the stream courses.
[read more: https://t.co/5F8ch71cJA]
[📹 Apoorva Rao: https://t.co/lCyBZiLeec]
With React Native v0.71 release we'll get:
- New app template is TypeScript by default
- TypeScript declarations shipped with React Native
- React Native documentation is TypeScript First
Great to see RN investing in what most of the community uses 👏
https://t.co/pqtuag2o0D