Written by Jakub Rusinowski · Last updated April 5, 2025
Yes, but it is tight
Yes, but it is tight — Llama 4 Scout 17B at Q6_K needs about 91.8 GB of the 96 GB usable on MacBook Pro 16" (M5 Max, 128 GB), leaving only ~4.2 GB before the runtime starts swapping. Expect ~21.4 tok/s (estimated), with room for about 16,384 tokens of context.
Confidence: medium · Recommended quantization: Q6_K · Estimated speed: ~21.4 tok/s
| Usable memory for models | 96 GB |
| Memory bandwidth | 614 GB/s |
| Form factor | Laptop |
| Operating system | macOS |
| Memory upgradeable | No — soldered |
| Quant | Memory needed | Fits 96 GB? | Max context | Est. speed | Download |
|---|---|---|---|---|---|
| F16 | 220.4 GB | ✗ No | — | — | 218 GB |
| Q8_0 | 118.2 GB | ✗ No | — | — | 115.8 GB |
| Q6_K | 91.8 GB | ✓ Yes | 16K | ~21.4 tok/s | 89.4 GB |
| Q5_K_M | 79.7 GB | ✓ Yes | 64K | ~24.3 tok/s | 77.3 GB |
| Q4_K_M | 68.2 GB | ✓ Yes | 128K | ~27.9 tok/s | 65.8 GB |
| Q3_K_M | 48.9 GB | ✓ Yes | 128K | ~37.1 tok/s | 46.5 GB |
| Q2_K | 38.2 GB | ✓ Yes | 256K | ~45.5 tok/s | 35.8 GB |
| Variant | Needs at Q4_K_M | Fits? | Est. speed |
|---|---|---|---|
| Llama 4 Maverick 17B | 243.9 GB | ✗ Too large | — |
| Llama 4 Scout 17B | 68.2 GB | ✓ Fits | ~27.9 tok/s |
Ollama or LM Studio (Metal) — MLX for the fastest Apple-native throughput
Yes, but it is tight — Llama 4 Scout 17B at Q6_K needs about 91.8 GB of the 96 GB usable on MacBook Pro 16" (M5 Max, 128 GB), leaving only ~4.2 GB before the runtime starts swapping. Expect ~21.4 tok/s (estimated), with room for about 16,384 tokens of context.
Q6_K — it needs about 91.8 GB of the 96 GB available, downloads as roughly 89.4 GB, and runs at an estimated 21.4 tokens/sec with up to 16K 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