Vitalik runs Qwen 3.8 Flash locally on his laptop, says local-first AI workflows are now viable
AnushElangovan · x · 2026-09-18
Ethereum founder Vitalik Buterin benchmarked Qwen 3.8 Flash running locally via llama.cpp on his Strix Halo laptop, calling it "truly impressive" and noting llama.cpp support is improving rapidly.
His take: we're very close to a point where local models can handle a large share of tasks, and privacy-preserving workflows — using your local model to orchestrate queries to powerful models so queries don't leak personal information — are becoming viable. The retweeter adds this validates pairing hardware like Halo with Qwen Flash.
Related event: Vitalik Buterin Tests Qwen 3.8 Flash Locally on a Laptop, Impressed(2 posts)→
More from Infra
- Big Tech's Future Data Center Leases Top $1.3T, 70% Added in Last Four Quarters — rohanpaul_ai · 2026-11-02
- Daniel Lemire: AI is exploding demand for boring compute, server CPUs to double — lemire · 2026-11-02
- Physical AI's real story: a 4-layer map of 15 companies behind humanoid robots — pdamodaran · 2026-11-02
- Under 5% of US consumers pay for AI, yet compute demand is already forcing usage cuts — NinaDSchick · 2026-11-02
- Sam Altman: AI query energy cost fell 1,000x-100,000x in 3-4 years — rohanpaul_ai · 2026-11-02
- Marvell and Lumentum to merge, targeting $550B AI connectivity market — BenBajarin · 2026-11-02