Can I Run Codestral on Apple M4 Pro?
Autor: Jakub Rusinowski · Ostatnia aktualizacja: 12 lipca 2026
Yes, comfortably — Codestral 22B at Q4_K_M needs 16.1 GB at 8K context (13.4 GB weights + 2.7 GB KV cache/overhead), leaving ~1.9 GB of the Apple M4 Pro's 18 GB usable memory, at ~10 tok/s (est.), with room for up to 16K context.
See what else this hardware can run →
lub porównaj w Vast.ai od $0.35/godz. (typical low · varies)
Jako partner Amazon zarabiamy na kwalifikujących się zakupach. Linki do chmurowych GPU są linkami polecającymi — możemy otrzymać prowizję bez dodatkowych kosztów dla Ciebie.
Apple M4 Pro Specs
| VRAM | 24 GB unified memory |
| Memory Bandwidth | 273 GB/s |
Codestral 22B on the Apple M4 Pro: VRAM by quantization
| Quant | VRAM needed | Fits 24 GB? | Max context | Whole PC |
|---|---|---|---|---|
| F16 | 47.1 GB | ✗ No | — | — |
| Q8_0 | 26.3 GB | ✗ No | — | — |
| Q6_K | 20.9 GB | ✗ No | — | — |
| Q5_K_M | 18.4 GB | ✗ No | — | — |
| Q4_K_M | 16.1 GB | ✓ Yes | 16K | — |
| Q3_K_M | 12.1 GB | ✓ Yes | 32K | — |
| Q2_K | 10 GB | ✓ Yes | 32K | — |
Assumes an 8K-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 24 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 M4 Pro: 8K 16.1 GB · 32K 21.7 GB ✗. Past 32K it no longer fits 24 GB — a q8_0 KV cache buys roughly half of that back, which the calculator will price for you.
No compatible GPU? Codestral 22B on 16 GB of system RAM, CPU only: runs, but it is tight.
Codestral Sizes That Fit the Apple M4 Pro (at 8K context)
| Codestral 22B | Q4_K_M · 16.1 GB at 8K context · ~10 tok/s (est.) |
Codestral needs ~16 GB but this GPU has 24 GB. Rent a RTX 4090 (24 GB)-class GPU by the hour instead of buying one:
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
Codestral on the Apple M4 Pro — does it fit?
Yes, comfortably — Codestral 22B at Q4_K_M needs 16.1 GB at 8K context (13.4 GB weights + 2.7 GB KV cache/overhead), leaving ~1.9 GB of the Apple M4 Pro's 18 GB usable memory, at ~10 tok/s (est.), with room for up to 16K context.
Which Codestral variant fits best on the Apple M4 Pro?
Codestral 22B at Q4_K_M quantization needs 16.1 GB at 8K context (13.4 GB weights + 2.7 GB KV cache/overhead), estimated ~10 tokens/sec, up to 16K context.
Codestral on Other GPUs
- Codestral on NVIDIA GeForce RTX 4090
- Codestral on NVIDIA GeForce RTX 3090
- Codestral on AMD Radeon RX 7900 XTX
- Codestral on Apple M3
- Codestral on Apple M2
VRAM Tier
Troubleshooting
Buying Guide
← Can I Run It? | Codestral Model Page | Apple M4 Pro GPU Page | VRAM calculator | Check Your Hardware