Can GLM 5.1 run on the Mac M3 Ultra 512GB?
Yes. At 8K context the best fit is Q3_K_M, using about 317 GB of the 384 GB usable on the Mac M3 Ultra 512GB. Estimated speed ceiling: ~43 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) | 264 GB Fits | 265 GB Fits | 267 GB Fits | 277 GB Fits | 52 |
| 3-bit (Q3_K_M) • | 316 GB Fits | 317 GB Fits | 319 GB Fits | 329 GB Fits | 43 |
| 4-bit (Q4_K_M) • | 434 GB No | 434 GB No | 437 GB No | 447 GB No | — |
| 5-bit (Q5_K_M) • | 521 GB No | 522 GB No | 524 GB No | 534 GB No | — |
| 6-bit (Q6_K) • | 580 GB No | 580 GB No | 583 GB No | 593 GB No | — |
| 8-bit (Q8_0) • | 747 GB No | 748 GB No | 750 GB No | 760 GB No | — |
| 16-bit (F16/BF16) • | 1406 GB No | 1406 GB No | 1408 GB No | 1419 GB No | — |
• real GGUF file size from unsloth/GLM-5.1-GGUF. Speed is a bandwidth ceiling (819 GB/s), not a benchmark. Methodology.
More
GLM 5.1 on every GPU and Mac · Every model that runs on the Mac M3 Ultra 512GB · Apple Silicon guide · Try other settings in the calculator
Data: Hugging Face Hub (zai-org/GLM-5.1), Apple specs. Data as of 2026-11-17.