Model Anatomy See what's inside open-weight AI models

Can I run Qwen3.8-35B-A3B-Distill on a Mac with 32 GB?

Yes, with a GGUF version

The published weights are too big, but the IQ4_XS file from empero-ai/Qwen3.8-35B-A3B-Distill-GGUF (19.6 GB) fits, with room for ≈ 78K tokens of context.

Full analysis of Qwen3.8-35B-A3B-Distill Everything that runs on Mac with 32 GB Get the IQ4_XS file on Hugging Face
ollama run hf.co/empero-ai/Qwen3.8-35B-A3B-Distill-GGUF:IQ4_XS

Files and context on Mac with 32 GB

Each file of Qwen3.8-35B-A3B-Distill (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.

FileSizeOn Mac with 32 GB Context (16-bit)Context (8-bit)
As published71.9 GBDoesn't fit——
BF16empero-ai/Qwen3.8-35B-A3B-Distill-GGUF71.1 GBDoesn't fit——
Q8_0empero-ai/Qwen3.8-35B-A3B-Distill-GGUF37.8 GBDoesn't fit——
Q6_Kempero-ai/Qwen3.8-35B-A3B-Distill-GGUF29.2 GBDoesn't fit——
Q5_K_Mempero-ai/Qwen3.8-35B-A3B-Distill-GGUF25.3 GBDoesn't fit——
Q4_K_Mempero-ai/Qwen3.8-35B-A3B-Distill-GGUF21.7 GBDoesn't fit——
IQ4_XSempero-ai/Qwen3.8-35B-A3B-Distill-GGUF19.6 GBTight78K157K
Q3_K_Mempero-ai/Qwen3.8-35B-A3B-Distill-GGUF17.7 GBTight172K256K
IQ3_Mempero-ai/Qwen3.8-35B-A3B-Distill-GGUF16.3 GBFits235K256K
Q2_Kempero-ai/Qwen3.8-35B-A3B-Distill-GGUF13.8 GBFits256K256K
IQ2_Mempero-ai/Qwen3.8-35B-A3B-Distill-GGUF12.6 GBFits256K256K

Qwen3.8-35B-A3B-Distill on other hardware

Popular models that run on Mac with 32 GB

Assumes 67% 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.