How to run Qwen 3.5 locally

Re:How to run Qwen 3.5 locally by bluerooibos on Sunday March 08, 2026 @02:01PM (#47299453)

These smaller models are fine for Q&A type stuff but are basically unuseable for anything agentic like large file modifications, coding, second brain type stuff - they need so much handholding. I'd be interested to see a demo of what the larger versions can do on better hardware though.

[ Parent | on HN ]

Re:How to run Qwen 3.5 locally by NorwegianDude on Sunday March 08, 2026 @03:56PM (#47300731)

Qwen3.5 27B works very well, to the point that if you use money on Claude 4.5 Haiku you could save hundreds of USD each day by running it yourself on a consumer GPU at home.

[ Parent | on HN ]

Re:How to run Qwen 3.5 locally by bluerooibos on Monday March 09, 2026 @07:37PM (#47317292)

Compared to Opus 4.6 though? And what sort of hardware/RAM is that running on - I'm assuming 32 or 64GB at least, right?

[ Parent | on HN ]

Re:How to run Qwen 3.5 locally by regularfry on Sunday March 08, 2026 @02:44PM (#47299852)

In some ways the handholding is the point. The way I used qwen2.5-coder in the past was as a rubber duck that happens to be able to type. You have to be in the loop with it, it's just a different style of agent use to what you might do with copilot or Claude.

[ Parent | on HN ]