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

Can Mage VL Cowork run on the Mac M2 Max 96GB?

Yes. At 8K context the best fit is F16, using about 10.0 GB of the 72.0 GB usable on the Mac M2 Max 96GB. Estimated speed ceiling: ~45 tokens/sec.

+ 0.3 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: F16 at 8K context then needs about 10.4 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)2.9 GB Fits3.5 GB Fits6.8 GB Fits20.3 GB Fits225
3-bit (Q3_K_M)3.4 GB Fits4.0 GB Fits7.3 GB Fits20.8 GB Fits173
4-bit (Q4_K_M) •3.8 GB Fits4.3 GB Fits7.7 GB Fits21.2 GB Fits147
5-bit (Q5_K_M)4.4 GB Fits5.0 GB Fits8.3 GB Fits21.8 GB Fits118
6-bit (Q6_K)4.9 GB Fits5.4 GB Fits8.8 GB Fits22.3 GB Fits103
8-bit (Q8_0) •5.6 GB Fits6.2 GB Fits9.6 GB Fits23.1 GB Fits85
16-bit (F16/BF16) •9.5 GB Fits10.0 GB Fits13.4 GB Fits26.9 GB Fits45

• real GGUF file size from ggml-org/Mage-VL-Cowork-GGUF. Speed is a bandwidth ceiling (400 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

Mage VL Cowork on every GPU and Mac · Every model that runs on the Mac M2 Max 96GB · 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 (microsoft/Mage-VL-Cowork), Apple specs. Model data last checked 2026-11-18; refreshed hourly.