Can I run QwQ-32B on a Mac with 48 GB?

Yes, with a GGUF version

The published weights are too big, but the Q8_0 file from Qwen/QwQ-32B-GGUF (34.8 GB) fits, with room for ≈ 4K tokens of context.

Full analysis of QwQ-32B Everything that runs on Mac with 48 GB Get the Q8_0 file on Hugging Face

ollama run hf.co/Qwen/QwQ-32B-GGUF:Q8_0

Files and context on Mac with 48 GB

Each file of QwQ-32B (and of GGUF versions the site has analyzed), and how much context fits next to it, with the context cache in 16-bit or 8-bit.

File	Size	On Mac with 48 GB	Context (16-bit)	Context (8-bit)
As published	65.5 GB	Doesn't fit	—	—
qwq-32b-fp16Qwen/QwQ-32B-GGUF	65.5 GB	Doesn't fit	—	—
Q8_0Qwen/QwQ-32B-GGUF	34.8 GB	Tight	4K	9K
Q6_KQwen/QwQ-32B-GGUF	26.9 GB	Fits	34K	68K
Q5_K_MQwen/QwQ-32B-GGUF	23.3 GB	Fits	47K	95K
Q5_0Qwen/QwQ-32B-GGUF	22.6 GB	Fits	50K	100K
Q4_K_MQwen/QwQ-32B-GGUF	19.9 GB	Fits	60K	120K

QwQ-32B on other hardware

Popular models that run on Mac with 48 GB

Assumes 75% of the Mac's memory is usable (macOS's default limit for the GPU; it can be raised) and at least 4K tokens of context for one conversation, with the context cache in 16-bit unless noted. Fits leaves at least 20% of that memory for context; Tight leaves less.