These speed gains are substantial. At 256K context lengths, Qwen 3.5 decodes 19 times faster than Qwen3-Max and 7.2 times ...

Mirai raised a $10 million seed to improve how AI models run on devices like smartphones and laptops.

The new lineup includes 30-billion and 105-billion parameter models; a text-to-speech model; a speech-to-text model; and a vision model to parse documents.

While the CEO did not actually name the product, something based on the Rubin architecture isn't exactly a bad guess. Rubin was first teased back in June 2024 at Computex and formally unveiled at GTC ...