RunsOnMy ModelsGPUs & MacsBy VRAMBest GPUCan I run…?OllamaStart hereAPI pricesVRAM calculatorNew

Can Gemma 4 26B A4B IT run on the Mac M1 Pro 32GB?

Yes. At 8K context the best fit is Q4_K_M, using about 17.3 GB of the 21.4 GB usable on the Mac M1 Pro 32GB. Estimated speed ceiling: ~76 tokens/sec.

+ 1.1 GB with image input. The figures on this page are for text only. With image input enabled, the vision projector (mmproj) file loads alongside the model: Q4_K_M at 8K context then needs about 18.4 GB (still fits). llama.cpp's -hf downloads and loads it automatically unless you add --no-mmproj. Calculator with image input on.

Memory by quant and context

Quant4K ctx8K ctx32K ctx128K ctxMax tok/s (est., 8K)
2-bit (Q2_K) •11.5 GB Fits11.6 GB Fits12.5 GB Fits16.3 GB Fits118
3-bit (Q3_K_M) •13.4 GB Fits13.5 GB Fits14.5 GB Fits18.2 GB Fits99
4-bit (Q4_K_M) •17.1 GB Fits17.3 GB Fits18.2 GB Fits22.0 GB No76
5-bit (Q5_K_M) •19.2 GB Fits19.4 GB Tight20.3 GB Tight24.1 GB No67
6-bit (Q6_K) •22.5 GB No22.7 GB No23.6 GB No27.4 GB No—
8-bit (Q8_0) •26.3 GB No26.4 GB No27.4 GB No31.1 GB No—
16-bit (F16/BF16) •48.3 GB No48.4 GB No49.4 GB No53.1 GB No—

• real GGUF file size from bartowski/google_gemma-4-26B-A4B-it-GGUF. Speed is a bandwidth ceiling (200 GB/s), not a benchmark. Methodology.

What fits instead

"Runs" and "fits" mean the whole model in GPU memory at 8K context (4-bit or better for the model pick). Prices are US launch MSRPs, not today's street prices. "Popular" means the 60 most-downloaded models we track.

More

Gemma 4 26B A4B IT on every GPU and Mac · Every model that runs on the Mac M1 Pro 32GB · Apple Silicon guide · Try other settings in the calculator

Guides: Best GPU for local LLMs by budget · Can I run gpt-oss, Llama 70B or Qwen3? · Mac vs PC for local LLMs

Data: Hugging Face Hub (google/gemma-4-26B-A4B-it), Apple specs. Model data last checked 2026-11-18; refreshed hourly.