Can I Run Codestral on Apple M2 Pro?
作者： Jakub Rusinowski · 最后更新： 2026年7月12日
Yes, comfortably — you'll have ~18.6 GB of headroom running Codestral 22B at Q4_K_M (13.4 GB, ~7 tok/s (est.)) with room for up to 32K context.
See what else this hardware can run →
或在 Vast.ai 比较，低至 $0.35/小时 (typical low · varies)
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。
Apple M2 Pro Specs
| VRAM | 32 GB unified memory |
| Memory Bandwidth | 200 GB/s |
Codestral 22B on the Apple M2 Pro: VRAM by quantization
| Quant | VRAM needed | Fits 32 GB? | Max context | Whole PC |
|---|---|---|---|---|
| F16 | 46.1 GB | ✗ No | — | — |
| Q8_0 | 25.3 GB | ✓ Yes | 32K | — |
| Q6_K | 19.9 GB | ✓ Yes | 32K | — |
| Q5_K_M | 17.5 GB | ✓ Yes | 32K | — |
| Q4_K_M | 15.1 GB | ✓ Yes | 32K | — |
| Q3_K_M | 11.2 GB | ✓ Yes | 32K | — |
| Q2_K | 9 GB | ✓ Yes | 32K | — |
Assumes a 4K-token context with an f16 KV cache. A longer window needs more; a quantized KV cache needs less. “Max context” is the largest window that still fits in 32 GB of unified memory. Figures are estimates from parameter count, quantization and memory bandwidth — the analyzer lets you tune KV-cache quant and context.
Context costs VRAM too. At Q4_K_M on the Apple M2 Pro: 8K 16.1 GB · 32K 21.7 GB. Every window this model publishes still fits 32 GB.
No compatible GPU? Codestral 22B on 16 GB of system RAM, CPU only: runs, but it is tight.
Codestral Sizes That Fit the Apple M2 Pro
| Codestral 22B | Q4_K_M · 13.4 GB · ~7 tok/s (est.) |
At 2 hrs/day, buying (~$1,999) beats renting at $0.34/hr after about 8.2 years.
Affiliate links — we may earn a commission if you sign up, at no extra cost to you.
Cloud rates verified 2026-07 — estimates, and marketplace prices vary. Buying price is GPU MSRP only, not a full PC.
FAQ
Is the Apple M2 Pro enough to run Codestral locally?
Yes, comfortably — you'll have ~18.6 GB of headroom running Codestral 22B at Q4_K_M (13.4 GB, ~7 tok/s (est.)) with room for up to 32K context.
What's the best Codestral size for the Apple M2 Pro?
Codestral 22B at Q4_K_M quantization (13.4 GB), estimated ~7 tokens/sec, up to 32K context.
Codestral on Other GPUs
- Codestral on NVIDIA GeForce RTX 5090
- Codestral on Apple M4
- Codestral on Apple M1 Pro
- Codestral on Apple M5
Popular Models on the Apple M2 Pro
VRAM Tier
Troubleshooting
Buying Guide
← Can I Run It? | Codestral Model Page | Apple M2 Pro GPU Page | Check Your Hardware