Written by Jakub Rusinowski · Last updated June 3, 2026
Yes — comfortably
Yes, comfortably — Gemma 4 31B at Q8_0 needs about 35.5 GB of the 144 GB usable on Mac Studio (M2 Ultra, 192 GB), leaving ~108.5 GB spare and running at ~12.5 tok/s (estimated), with room for about 131,072 tokens of context.
Confidence: medium · Recommended quantization: Q8_0 · Estimated speed: ~12.5 tok/s
| Usable memory for models | 144 GB |
| Memory bandwidth | 800 GB/s |
| Form factor | Desktop |
| Operating system | macOS |
| Memory upgradeable | No — soldered |
| Quant | Memory needed | Fits 144 GB? | Max context | Est. speed | Download |
|---|---|---|---|---|---|
| F16 | 64.6 GB | ✓ Yes | 128K | ~6.8 tok/s | 62 GB |
| Q8_0 | 35.5 GB | ✓ Yes | 128K | ~12.5 tok/s | 32.9 GB |
| Q6_K | 28 GB | ✓ Yes | 128K | ~15.9 tok/s | 25.4 GB |
| Q5_K_M | 24.6 GB | ✓ Yes | 128K | ~18.1 tok/s | 22 GB |
| Q4_K_M | 21.3 GB | ✓ Yes | 128K | ~20.9 tok/s | 18.7 GB |
| Q3_K_M | 15.8 GB | ✓ Yes | 128K | ~28.4 tok/s | 13.2 GB |
| Q2_K | 12.8 GB | ✓ Yes | 128K | ~35.3 tok/s | 10.2 GB |
| Variant | Needs at Q4_K_M | Fits? | Est. speed |
|---|---|---|---|
| Gemma 4 31B | 21.3 GB | ✓ Fits | ~20.9 tok/s |
| Gemma 4 26B-A4B | 18.2 GB | ✓ Fits | ~95.6 tok/s |
| Gemma 4 12B (Unified) | 9.4 GB | ✓ Fits | ~47.6 tok/s |
| Gemma 4 E4B | 6.8 GB | ✓ Fits | ~65.3 tok/s |
| Gemma 4 E2B | 4.9 GB | ✓ Fits | ~89.5 tok/s |
Ollama or LM Studio (Metal) — MLX for the fastest Apple-native throughput
Yes, comfortably — Gemma 4 31B at Q8_0 needs about 35.5 GB of the 144 GB usable on Mac Studio (M2 Ultra, 192 GB), leaving ~108.5 GB spare and running at ~12.5 tok/s (estimated), with room for about 131,072 tokens of context.
Q8_0 — it needs about 35.5 GB of the 144 GB available, downloads as roughly 32.9 GB, and runs at an estimated 12.5 tokens/sec with up to 128K 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