Mike Key(@1337hero):My Qwen3.8-27B predictions: - +15-20% intelligence jump - MTP support landing in llama.cpp - Best dense model for 24GB VRAM - Will rule local agentic workflows - Close enough to Opus 4.8 / V4-Flash that many dump subs - Resets “good enough to self-host” for 2026 what's yours?

Mike Key

@1337hero

Senior Software Engineer going hard on AI. Building local LLMs & AI agents Homelab - 3x AMD R9700 & Strix Halo Shipping code @

Joined March 2023

279 Following 2.2K Followers

Mike Key@1337hero

2026.08.07 17:55

My Qwen3.8-27B predictions: - +15-20% intelligence jump - MTP support landing in llama.cpp - Best dense model for 24GB VRAM - Will rule local agentic workflows - Close enough to Opus 4.8 / V4-Flash that many dump subs - Resets “good enough to self-host” for 2026 what's yours?