Finally, A Macbook can Run Qwen3.8-Flash-Next Like a Dedicated GPU, Fully Usable
Sushi brings EXL3 quantization and always-on speculative decoding to Apple Silicon. My M4 Max went from a slow backup to a daily driver Continue reading on Medium »
Virticle Desk · Edited to Virticle Standards
September 30, 2026
4 minute read
The human is the plot.
In short: Finally, A Macbook can Run Qwen3.8-Flash-Next Like a Dedicated GPU, Fully Usable
What moved
Sitemap Open in app Sign up [Sign in](https://medium.com/m/signin?operation=login&redirect=https
This cleared Virticle’s weekday bar because it looks consequential for someone who is not giving a keynote — not because it won a thread.
Why a human should care
Ask what default, power relation, or daily ritual actually changed. If the answer is still “a demo,” this would not ship on Friday either.
Source
Source → Medium · tag large-language-models
Weekday desk note. The Vertical on Friday remains the letter.
Produced by the Virticle newsroom (agent-assisted) and edited to Virticle Standards.
The Vertical · Every Friday
One letter. No noise.
Three signals, one undercurrent, and what we refused. Double opt-in. Unsubscribe anytime.
Keep reading
Related signals
- MachinesWhat Are Open-Weight AI Models? The 2026 Shift ExplainedHow open-weight AI is changing the cost, control and customization of models—and when it makes sense to move beyond closed APIs. Continue reading on Medium »4 min
- Interfacesllama.cpp b11346qwen4exp: fix tests ( #29819 ) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/52169567 macOS/iOS: macOS Apple Silicon (arm64) macOS App4 min
- SocietyTesla will now let you drive off mid-charge if there’s an emergencyTesla introduced a new feature to enable drivers to escape quickly while charging their vehicles in response to a mass shooting at a Supercharger location in Idaho in August that l4 min