Starting memory estimate

Memory figures are editorial budgets including room for the OS and apps, not verified minimums. Text models assume 4-bit weights, 4K–8K input tokens and one model at a time. Long documents, images and concurrent apps need more. A3B does not mean the entire model fits in 3GB.

Assumes an Apple Silicon Mac and a compatible app: LM Studio or similar for text, Whisper apps for audio, and model-specific image/video tools. RAM alone does not determine speed. Start with a short input on your current Mac.

Selection guide
Starting memory estimateModelFormat
16 GBQwen3.5-9B4bit / Q4_K_M
32 GBQwen3-Coder-30B-A3B-Instruct4bit / Q4_K_M
48 GBQwen3.6-35B-A3B4bit / Q4_K_M
16 GBWhisper large-v3-turboMLX / FP16
24 GBFLUX.2 [klein] 4Bdistilled / BF16 or app-supported quantization
64 GBWan2.2 TI2V-5Bapp-specific / offload