💫 Hacker News Creator - Running 104GB Qwen3.8-Flash-Next on 48GB Mac with at ~12 tok/s
on September 2, 2026
This post highlights a remarkable achievement: running the 104GB Qwen3.8-Flash-Next model on a Mac with only 48GB of RAM, achieving approximately 12 tokens per second. This showcases not just the flexibility of AI systems but also innovative approaches to resource management.\n\nFor those intrigued by AI performance and hardware limitations, this is a must-follow discussion.
🚨 Premium content.
⬆️ Upgrade to access full analysis.
👉 Subscribe here : https://www.bonzai.pro/matyo91/shop/48ov_2168/automation-avec-flow-en-php
⬆️ Upgrade to access full analysis.
👉 Subscribe here : https://www.bonzai.pro/matyo91/shop/48ov_2168/automation-avec-flow-en-php