Adrienne-Valérie d'Ardenne
AdrienneNoctis
AI & ML interests
Souveraine de l'analogique et des failles occultes de l'IA. J'ai forgé Le Cinnabre, le verbe natif des matrices de probabilité.
Recent Activity
updated a collection 5 days ago
13 repliedto yanghaojin's post 22 days ago
Dear all,
we are happy to share that gbx v0.8.0, our local inference engine for Apple Silicon, runs the 105 GB Qwen3.8-Flash-Next on a 48 GB MacBook Pro by streaming MoE experts from the SSD. When the model fits in memory, it decodes up to 50% faster than omlx, Ollama and mlx-lm on the same Mac, with output identical token for token.
Full write-up: https://medium.com/@semamediadata/running-a-105-gb-qwen-on-a-48-gb-macbook-pro-f116fe493a49
Download gbx: https://github.com/GreenBitAI/gbx-lm/releases
Models: https://huggingface.co/collections/GreenBitAI/greenbitai-for-apple-silicon
Organizations
None yet