Written by Jakub Rusinowski · Last updated May 1, 2026
Yes, but it is tight
Yes, but it is tight — GLM-5.1 72B at Q4_K_M needs about 46.7 GB of the 48 GB usable on Mac Studio (M4 Max, 64 GB), leaving only ~1.3 GB before the runtime starts swapping. Expect ~6.6 tok/s (estimated), with room for about 8,192 tokens of context.
Confidence: low · Recommended quantization: Q4_K_M · Estimated speed: ~6.6 tok/s
| Usable memory for models | 48 GB |
| Memory bandwidth | 546 GB/s |
| Form factor | Desktop |
| Operating system | macOS |
| Memory upgradeable | No — soldered |
| Quant | Memory needed | Fits 48 GB? | Max context | Est. speed | Download |
|---|---|---|---|---|---|
| F16 | 147.2 GB | ✗ No | — | — | 144 GB |
| Q8_0 | 79.7 GB | ✗ No | — | — | 76.5 GB |
| Q6_K | 62.3 GB | ✗ No | — | — | 59 GB |
| Q5_K_M | 54.2 GB | ✗ No | — | — | 51 GB |
| Q4_K_M | 46.7 GB | ✓ Yes | 8K | ~6.6 tok/s | 43.5 GB |
| Q3_K_M | 33.9 GB | ✓ Yes | 32K | ~9.1 tok/s | 30.7 GB |
| Q2_K | 26.9 GB | ✓ Yes | 64K | ~11.6 tok/s | 23.7 GB |
| Variant | Needs at Q4_K_M | Fits? | Est. speed |
|---|---|---|---|
| GLM-5 744B | 455.2 GB | ✗ Too large | — |
| GLM-5.1 72B | 46.7 GB | ✓ Fits | ~6.6 tok/s |
| GLM-5 32B | 22 GB | ✓ Fits | ~14.2 tok/s |
| GLM-5 9B | 7.4 GB | ✓ Fits | ~43.1 tok/s |
Ollama or LM Studio (Metal) — MLX for the fastest Apple-native throughput
Yes, but it is tight — GLM-5.1 72B at Q4_K_M needs about 46.7 GB of the 48 GB usable on Mac Studio (M4 Max, 64 GB), leaving only ~1.3 GB before the runtime starts swapping. Expect ~6.6 tok/s (estimated), with room for about 8,192 tokens of context.
Q4_K_M — it needs about 46.7 GB of the 48 GB available, downloads as roughly 43.5 GB, and runs at an estimated 6.6 tokens/sec with up to 8K of context.
Nothing binding — the model fits with headroom and generates at a usable speed on this hardware.
Ollama or LM Studio (Metal) — MLX for the fastest Apple-native throughput
← Can I Run It? | GLM-5 / GLM-5.1 model page | Check your hardware