Can Llama Guard 4 12B run on the Mac M4 Pro 64GB?
Yes. At 8K context the best fit is F16, using about 24.6 GB of the 48.0 GB usable on the Mac M4 Pro 64GB. Estimated speed ceiling: ~11 tokens/sec.
Memory by quant and context
| Quant | 4K ctx | 8K ctx | 32K ctx | 128K ctx | Max tok/s (est., 8K) |
|---|---|---|---|---|---|
| 2-bit (Q2_K) | 5.7 GB Fits | 6.5 GB Fits | 11.0 GB Fits | 29.0 GB Fits | 61 |
| 3-bit (Q3_K_M) | 7.0 GB Fits | 7.7 GB Fits | 12.2 GB Fits | 30.2 GB Fits | 47 |
| 4-bit (Q4_K_M) | 8.4 GB Fits | 9.1 GB Fits | 13.6 GB Fits | 31.6 GB Fits | 37 |
| 5-bit (Q5_K_M) | 9.5 GB Fits | 10.2 GB Fits | 14.7 GB Fits | 32.7 GB Fits | 32 |
| 6-bit (Q6_K) | 10.7 GB Fits | 11.5 GB Fits | 16.0 GB Fits | 34.0 GB Fits | 28 |
| 8-bit (Q8_0) | 13.4 GB Fits | 14.2 GB Fits | 18.7 GB Fits | 36.7 GB Fits | 21 |
| 16-bit (F16/BF16) | 23.9 GB Fits | 24.6 GB Fits | 29.1 GB Fits | 47.1 GB Tight | 11 |
• real GGUF file size. Speed is a bandwidth ceiling (273 GB/s), not a benchmark. Methodology.
More
Llama Guard 4 12B on every GPU and Mac · Every model that runs on the Mac M4 Pro 64GB · Apple Silicon guide · Try other settings in the calculator
Data: Hugging Face Hub (meta-llama/Llama-Guard-4-12B), Apple specs. Data as of 2026-11-17.