Can I Run Codestral on MacBook Air (M4, 16 GB)?

作者: Jakub Rusinowski · 最后更新: 2024年5月29日

Yes

Yes — Codestral 22B at Q2_K needs about 10 GB of the 12 GB usable on MacBook Air (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

See what else this hardware can run →

MacBook Air (M4, 16 GB) — what it gives a model

Usable memory for models12 GB
Memory bandwidth120 GB/s
Form factorLaptop
Operating systemmacOS
Memory upgradeableNo — soldered

Codestral on MacBook Air (M4, 16 GB): memory by quantization

QuantMemory neededFits 12 GB?Max contextEst. speedDownload
F1647.1 GB✗ No——44.4 GB
Q8_026.3 GB✗ No——23.6 GB
Q6_K20.9 GB✗ No——18.2 GB
Q5_K_M18.4 GB✗ No——15.7 GB
Q4_K_M16.1 GB✗ No——13.4 GB
Q3_K_M12.1 GB✗ No——9.5 GB
Q2_K10 GB✓ Yes16K~7.8 tok/s7.3 GB
Superseded model. Codestral has been superseded by Devstral. This page is kept for reference; the newer family is a better starting point. Devstral needs at least 16.6 GB at Q4_K_M with an 8K context, so it does not fit the MacBook Air (M4, 16 GB).

What to watch out for

MacBook Air M4 16 GB limitations

Recommended setup

Ollama or LM Studio (Metal) — MLX for the fastest Apple-native throughput

How these numbers are calculated

FAQ

Can I run Codestral on MacBook Air (M4, 16 GB)?

Yes — Codestral 22B at Q2_K needs about 10 GB of the 12 GB usable on MacBook Air (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 MacBook Air (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 MacBook Air (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 MacBook Air (M4, 16 GB)

Codestral on GPUs

What This Model Is Good At

Model & Tools

← Can I Run It? | Codestral model page | Check your hardware