Qwen3.5-Medium: Frontier AI Performance on a Gaming PC
Alibaba's new 35B model matches Claude Sonnet 4.5 on benchmarks while running locally on an RTX 4090. Here's what you need to know.
Tag
#mixture-of-experts
Alibaba's Qwen 3.5: A Frontier Model You Can Run Yourself (With Some Caveats)
Alibaba released Qwen 3.5 under Apache 2.0, claiming GPT-5.2 parity. The 397B-parameter model runs on consumer hardware through smaller variants - but comes with documented censorship patterns.