Written by Jakub Rusinowski · Last updated November 26, 2024
Yes — comfortably
Yes, comfortably — OLMo 2 13B Instruct at Q8_0 needs about 22.1 GB of the 192 GB usable on Mac Studio (M3 Ultra, 256 GB), leaving ~169.9 GB spare and running at ~23.3 tok/s (estimated), with room for about 4,096 tokens of context.
Confidence: high · Recommended quantization: Q8_0 · Estimated speed: ~23.3 tok/s
| Usable memory for models | 192 GB |
| Memory bandwidth | 819 GB/s |
| Form factor | Desktop |
| Operating system | macOS |
| Memory upgradeable | No — soldered |
| Quant | Memory needed | Fits 192 GB? | Max context | Est. speed | Download |
|---|---|---|---|---|---|
| F16 | 34.9 GB | ✓ Yes | 4K | ~14 tok/s | 27.4 GB |
| Q8_0 | 22.1 GB | ✓ Yes | 4K | ~23.3 tok/s | 14.6 GB |
| Q6_K | 18.7 GB | ✓ Yes | 4K | ~28.2 tok/s | 11.2 GB |
| Q5_K_M | 17.2 GB | ✓ Yes | 4K | ~31.1 tok/s | 9.7 GB |
| Q4_K_M | 15.8 GB | ✓ Yes | 4K | ~34.6 tok/s | 8.3 GB |
| Q3_K_M | 13.4 GB | ✓ Yes | 4K | ~42.6 tok/s | 5.8 GB |
| Q2_K | 12 GB | ✓ Yes | 4K | ~48.8 tok/s | 4.5 GB |
| Variant | Needs at Q4_K_M | Fits? | Est. speed |
|---|---|---|---|
| OLMo 2 13B Instruct | 15.8 GB | ✓ Fits | ~34.6 tok/s |
| OLMo 2 7B Instruct | 9.5 GB | ✓ Fits | ~56.8 tok/s |
Ollama or LM Studio (Metal) — MLX for the fastest Apple-native throughput
Yes, comfortably — OLMo 2 13B Instruct at Q8_0 needs about 22.1 GB of the 192 GB usable on Mac Studio (M3 Ultra, 256 GB), leaving ~169.9 GB spare and running at ~23.3 tok/s (estimated), with room for about 4,096 tokens of context.
Q8_0 — it needs about 22.1 GB of the 192 GB available, downloads as roughly 14.6 GB, and runs at an estimated 23.3 tokens/sec with up to 4K 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