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

Can Llama 3.3 70B Instruct run on the Mac M2 Ultra 192GB?

Yes. At 8K context the best fit is Q8_0, using about 73.0 GB of the 144 GB usable on the Mac M2 Ultra 192GB. Estimated speed ceiling: ~11 tokens/sec.

Memory by quant and context

Quant4K ctx8K ctx32K ctx128K ctxMax tok/s (est., 8K)
2-bit (Q2_K) •26.5 GB Fits27.7 GB Fits35.2 GB Fits65.2 GB Fits30
3-bit (Q3_K_M) •33.8 GB Fits35.1 GB Fits42.6 GB Fits72.6 GB Fits23
4-bit (Q4_K_M) •41.5 GB Fits42.7 GB Fits50.2 GB Fits80.2 GB Fits19
5-bit (Q5_K_M) •48.4 GB Fits49.7 GB Fits57.2 GB Fits87.2 GB Fits16
6-bit (Q6_K) •55.8 GB Fits57.1 GB Fits64.6 GB Fits94.6 GB Fits14
8-bit (Q8_0) •71.7 GB Fits73.0 GB Fits80.5 GB Fits110 GB Fits11
16-bit (F16/BF16) •133 GB Tight135 GB Tight142 GB Tight172 GB No6

• real GGUF file size from bartowski/Llama-3.3-70B-Instruct-GGUF. Speed is a bandwidth ceiling (800 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

Llama 3.3 70B Instruct on every GPU and Mac · Every model that runs on the Mac M2 Ultra 192GB · 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 (meta-llama/Llama-3.3-70B-Instruct), Apple specs. Model data last checked 2026-11-18; refreshed hourly.