Written by Jakub Rusinowski · Last updated April 28, 2025
Yes — comfortably
Yes, comfortably — Qwen 3 32B at Q8_0 needs about 37.8 GB of the 144 GB usable on Mac Studio (M2 Ultra, 192 GB), leaving ~106.2 GB spare and running at ~11.8 tok/s (estimated), with room for about 65,536 tokens of context.
Confidence: high · Recommended quantization: Q8_0 · Estimated speed: ~11.8 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 | 68.5 GB | ✓ Yes | 64K | ~6.4 tok/s | 65.6 GB |
| Q8_0 | 37.8 GB | ✓ Yes | 64K | ~11.8 tok/s | 34.8 GB |
| Q6_K | 29.8 GB | ✓ Yes | 64K | ~15 tok/s | 26.9 GB |
| Q5_K_M | 26.2 GB | ✓ Yes | 64K | ~17.1 tok/s | 23.2 GB |
| Q4_K_M | 22.8 GB | ✓ Yes | 64K | ~19.8 tok/s | 19.8 GB |
| Q3_K_M | 16.9 GB | ✓ Yes | 64K | ~26.8 tok/s | 14 GB |
| Q2_K | 13.7 GB | ✓ Yes | 64K | ~33.3 tok/s | 10.8 GB |
| Variant | Needs at Q4_K_M | Fits? | Est. speed |
|---|---|---|---|
| Qwen 3 235B-A22B (MoE) | 144.3 GB | ✗ Too large | — |
| Qwen 3 32B | 22.8 GB | ✓ Fits | ~19.8 tok/s |
| Qwen 3 30B-A3B (MoE) | 20 GB | ✓ Fits | ~118.2 tok/s |
| Qwen 3 14B | 11.1 GB | ✓ Fits | ~40.1 tok/s |
| Qwen 3 8B | 7 GB | ✓ Fits | ~63.8 tok/s |
Ollama or LM Studio (Metal) — MLX for the fastest Apple-native throughput
Yes, comfortably — Qwen 3 32B at Q8_0 needs about 37.8 GB of the 144 GB usable on Mac Studio (M2 Ultra, 192 GB), leaving ~106.2 GB spare and running at ~11.8 tok/s (estimated), with room for about 65,536 tokens of context.
Q8_0 — it needs about 37.8 GB of the 144 GB available, downloads as roughly 34.8 GB, and runs at an estimated 11.8 tokens/sec with up to 64K 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