Can I Run Magistral Small on Mac Studio (M4 Max, 64 GB)?
作者： Jakub Rusinowski · 最后更新： 2026年9月6日
Yes — comfortably
Yes, comfortably — Magistral Small 24B at Q8_0 needs about 28 GB of the 48 GB usable on Mac Studio (M4 Max, 64 GB), leaving ~20 GB spare and running at ~11 tok/s (estimated), with room for about 65,536 tokens of context.
Confidence: medium · Recommended quantization: Q8_0 · Estimated speed: ~11 tok/s
See what else this hardware can run →
作为亚马逊联盟成员，我们从符合条件的购买中获得收入。云 GPU 链接为推荐链接——我们可能获得佣金，您无需额外付费。
Mac Studio (M4 Max, 64 GB) — what it gives a model
| Usable memory for models | 48 GB |
| Memory bandwidth | 546 GB/s |
| Form factor | Desktop |
| Operating system | macOS |
| Memory upgradeable | No — soldered |
Magistral Small on Mac Studio (M4 Max, 64 GB): memory by quantization
| Quant | Memory needed | Fits 48 GB? | Max context | Est. speed | Download |
|---|---|---|---|---|---|
| F16 | 50.5 GB | ✗ No | — | — | 48 GB |
| Q8_0 | 28 GB | ✓ Yes | 64K | ~11 tok/s | 25.5 GB |
| Q6_K | 22.2 GB | ✓ Yes | 128K | ~14 tok/s | 19.7 GB |
| Q5_K_M | 19.5 GB | ✓ Yes | 128K | ~16 tok/s | 17 GB |
| Q4_K_M | 17 GB | ✓ Yes | 128K | ~18.4 tok/s | 14.5 GB |
| Q3_K_M | 12.7 GB | ✓ Yes | 128K | ~25 tok/s | 10.2 GB |
| Q2_K | 10.4 GB | ✓ Yes | 128K | ~31.1 tok/s | 7.9 GB |
What to watch out for
- This model does not publish its full attention configuration, so the KV-cache share of these figures is inferred from its parameter count rather than computed exactly.
- Memory on this machine is not upgradeable, so the configuration you buy is the ceiling for every model you will ever run on it.
Mac Studio M4 Max 64 GB limitations
- Memory is soldered; the configuration chosen at purchase is permanent.
Recommended setup
Ollama or LM Studio (Metal) — MLX for the fastest Apple-native throughput
How these numbers are calculated
- Memory need = quantized weights + KV cache at 8,192 tokens (f16) + 0.8 GB runtime overhead.
- 64 GB unified memory at 546 GB/s, shared between CPU and GPU.
- macOS reserves a share of unified memory for the system, so not all of it is available to a model.
- Throughput is a memory-bandwidth roofline estimate, not a measurement. It is labelled "estimated" everywhere it appears.
- KV cache is inferred from the parameter count because this model does not publish its full attention configuration.
FAQ
Can I run Magistral Small on Mac Studio (M4 Max, 64 GB)?
Yes, comfortably — Magistral Small 24B at Q8_0 needs about 28 GB of the 48 GB usable on Mac Studio (M4 Max, 64 GB), leaving ~20 GB spare and running at ~11 tok/s (estimated), with room for about 65,536 tokens of context.
Which quantization of Magistral Small should I use on Mac Studio (M4 Max, 64 GB)?
Q8_0 — it needs about 28 GB of the 48 GB available, downloads as roughly 25.5 GB, and runs at an estimated 11 tokens/sec with up to 64K of context.
What limits Magistral Small on Mac Studio (M4 Max, 64 GB)?
Nothing binding — the model fits with headroom and generates at a usable speed on this hardware.
Which runtime should I use?
Ollama or LM Studio (Metal) — MLX for the fastest Apple-native throughput
Other Computers
Other Models on Mac Studio (M4 Max, 64 GB)
- MiniCPM-V on Mac Studio (M4 Max, 64 GB)
- Ministral on Mac Studio (M4 Max, 64 GB)
- Ministral 3 on Mac Studio (M4 Max, 64 GB)
- Mistral Family on Mac Studio (M4 Max, 64 GB)
- Mistral Small 3.1 on Mac Studio (M4 Max, 64 GB)
Magistral Small on GPUs
- Magistral Small on NVIDIA GeForce RTX 5090
- Magistral Small on NVIDIA GeForce RTX 5080
- Magistral Small on NVIDIA GeForce RTX 5070 Ti
- Magistral Small on NVIDIA GeForce RTX 5070
What This Model Is Good At
Model & Tools
← Can I Run It? | Magistral Small model page | Check your hardware