Can I Run Codestral on Mac mini (M4, 16 GB)?
Superseded model. Codestral has been superseded by Devstral. This page is kept for reference; the newer family is a better starting point.
View Devstral →
Written by Jakub Rusinowski · Last updated May 29, 2024
Yes
Yes — Codestral 22B at Q2_K needs about 10 GB of the 12 GB usable on Mac mini (M4, 16 GB) (~2 GB spare), at ~7.8 tok/s (estimated), with room for about 16,384 tokens of context.
Confidence: high · Recommended quantization: Q2_K · Estimated speed: ~7.8 tok/s
Mac mini (M4, 16 GB) — what it gives a model
| Usable memory for models | 12 GB |
| Memory bandwidth | 120 GB/s |
| Form factor | Mini PC |
| Operating system | macOS |
| Memory upgradeable | No — soldered |
| Price | $599 (lib/data/ai-stations.ts (street price), checked 2026-07-06) |
Codestral on Mac mini (M4, 16 GB): memory by quantization
| Quant | Memory needed | Fits 12 GB? | Max context | Est. speed | Download |
|---|
| F16 | 47.1 GB | ✗ No | — | — | 44.4 GB |
| Q8_0 | 26.3 GB | ✗ No | — | — | 23.6 GB |
| Q6_K | 20.9 GB | ✗ No | — | — | 18.2 GB |
| Q5_K_M | 18.4 GB | ✗ No | — | — | 15.7 GB |
| Q4_K_M | 16.1 GB | ✗ No | — | — | 13.4 GB |
| Q3_K_M | 12.1 GB | ✗ No | — | — | 9.5 GB |
| Q2_K | 10 GB | ✓ Yes | 16K | ~7.8 tok/s | 7.3 GB |
What to watch out for
- Q2_K is the only quantization that fits, and it is a heavily degraded one — expect noticeably worse output than the same model at Q4_K_M. A smaller model at Q4 is usually the better trade.
- 1 larger variant of Codestral does not fit and would need CPU offload or different hardware.
- 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 mini M4 16 GB limitations
- The cheapest credible always-on local-AI box, but 16 GB caps it at small and mid-size models.
- Memory is soldered; upgrading means replacing the machine.
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.
- 16 GB unified memory at 120 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 computed from this model's published attention configuration.
FAQ
Can I run Codestral on Mac mini (M4, 16 GB)?
Yes — Codestral 22B at Q2_K needs about 10 GB of the 12 GB usable on Mac mini (M4, 16 GB) (~2 GB spare), at ~7.8 tok/s (estimated), with room for about 16,384 tokens of context.
Which quantization of Codestral should I use on Mac mini (M4, 16 GB)?
Q2_K — it needs about 10 GB of the 12 GB available, downloads as roughly 7.3 GB, and runs at an estimated 7.8 tokens/sec with up to 16K of context.
What limits Codestral on Mac mini (M4, 16 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 mini (M4, 16 GB)
Codestral on GPUs
What This Model Is Good At
Model & Tools
← Can I Run It? | Codestral model page | Check your hardware