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

Can I run gemma-4-26B-A4B-it-GGUF on a Mac with 32 GB?

Yes, just

Its UD-Q5_K_S file (18.9 GB) fits in the 21.3 GB a Mac with 32 GB can use, with room for ≈ 25K tokens of context.

Full analysis of gemma-4-26B-A4B-it-GGUF Everything that runs on Mac with 32 GB Get the UD-Q5_K_S file on Hugging Face
ollama run hf.co/unsloth/gemma-4-26B-A4B-it-GGUF:UD-Q5_K_S

Files and context on Mac with 32 GB

Each file of gemma-4-26B-A4B-it-GGUF (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)
BF1650.5 GBDoesn't fit——
UD-Q8_K_XL27.6 GBDoesn't fit——
Q8_026.9 GBDoesn't fit——
UD-Q6_K_XL23.3 GBDoesn't fit——
UD-Q6_K23.2 GBDoesn't fit——
UD-Q5_K_XL21.2 GBDoesn't fit235470
UD-Q5_K_M21.2 GBDoesn't fit372744
UD-Q5_K_S18.9 GBTight25K54K
UD-Q4_K_XL17.0 GBFits47K98K
UD-Q4_K_M16.9 GBFits47K100K
MXFP4_MOE16.6 GBFits52K109K
UD-Q4_K_S16.5 GBFits53K111K
UD-IQ4_NL13.6 GBFits87K179K
UD-IQ4_XS13.6 GBFits87K179K
UD-Q3_K_XL12.9 GBFits95K196K
UD-Q3_K_M12.7 GBFits98K200K
UD-IQ3_XXS11.4 GBFits113K231K
UD-IQ3_S11.3 GBFits115K234K
UD-Q2_K_XL10.5 GBFits124K252K
UD-IQ2_M10.0 GBFits130K256K
UD-IQ2_XXS9.92 GBFits131K256K

gemma-4-26B-A4B-it-GGUF 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.