What you need to run Qwen 3.5 122B A10B

About Qwen 3.5 122B A10B

Qwen 3.5 122B A10B is a general chat model from Alibaba. Near frontier quality at home, if you have 96 GB or more. Running it locally needs about 85.5 GB of memory, and the download is 81 GB. It is a mixture of experts model: only about 6.6 GB of its weights are read for each word, so it generates much faster than a dense model of the same size, but all 81 GB still has to fit in memory.

Smallest Mac that runs it

The least memory you need, by Apple chip:

• M1: does not fit
• M1 Pro: does not fit
• M1 Max: does not fit
• M1 Ultra: from 128 GB
• M2: does not fit
• M2 Pro: does not fit
• M2 Max: from 96 GB
• M2 Ultra: from 128 GB
• M3: does not fit
• M3 Pro: does not fit
• M3 Max: from 96 GB
• M3 Ultra: from 96 GB
• M4: does not fit
• M4 Pro: does not fit
• M4 Max: from 128 GB
• M5: does not fit
• M5 Pro: does not fit
• M5 Max: from 128 GB

Graphics cards

No single desktop graphics card runs it well.

Hardware to run it

As an Amazon Associate I earn from qualifying purchases.

• Smallest Mac: M3 Ultra with 96 GB. See it on Amazon
• No single desktop graphics card runs it well.
• Storage: this model is a 81 GB download, and most people end up keeping several. A fast external SSD keeps your main drive free. See SSDs on Amazon

Lighter and heavier alternatives

• Llama 3.3 70B: needs about 45.6 GB, a lighter choice. Older but solid large model. Needs serious memory.
• gpt-oss 120B: needs about 68.8 GB, a lighter choice. OpenAI's big open model. Fast for its size on high-memory machines.
• DeepSeek V3 671B: needs about 424.7 GB, a heavier choice. Frontier class. Needs a 512 GB Mac Studio or a server.

Questions