Apple · M3 · Laptop

Best AI Models for MacBook Air 13" M3 (16 GB)

Runs 9B models at 11 tok/s; 14B only just fits in 12.5 GB, and 27–31B doesn't fit.

16 GB unified12.5 GB for models102.4 GB/s7 TFLOPS FP162024

Memory

Same chip in

MacBook Air 13"iMac 24"MacBook Air 15"MacBook Pro 14"

What LLMs can the MacBook Air 13" M3 run?

#	Model	Speed	Quant · Memory
1	Qwen3.5 9BAlibabaHow to run → Q4_K_M · 6.6 GB · 11.3 t/s	11.3 tok/s	Q4_K_M · 6.6 GB
2	Qwen3.5 4BAlibaba Q4_K_M · 3.4 GB · 22.0 t/s	22.0 tok/s	Q4_K_M · 3.4 GB
3	Gemma 3 4B ITGoogle Q4_K_M · 5.0 GB · 25.2 t/s	25.2 tok/s	Q4_K_M · 5.0 GB
4	Ling 3.0 TinyInclusion AI Q4_K_M · 5.5 GB · 56.1 t/s	56.1 tok/s	Q4_K_M · 5.5 GB
5	Gemma 4 E2B ITGoogle Q4_K_M · 3.5 GB · 20.9 t/s	20.9 tok/s	Q4_K_M · 3.5 GB

#	Model	Speed	Reasoning Score	Quant · Memory
1	Gemma 3 4B ITGoogleHow to run → Q4_K_M · 5.0 GB · 25.2 t/s	25.2 tok/s		Q4_K_M · 5.0 GB
2	Qwen3.5 9BAlibaba Q4_K_M · 6.6 GB · 11.3 t/s	11.3 tok/s		Q4_K_M · 6.6 GB
3	Qwen3.5 4BAlibaba Q4_K_M · 3.4 GB · 22.0 t/s	22.0 tok/s	overall	Q4_K_M · 3.4 GB
4	Ling 3.0 TinyInclusion AI Q4_K_M · 5.5 GB · 56.1 t/s	56.1 tok/s		Q4_K_M · 5.5 GB
5	Gemma 4 E2B ITGoogle Q4_K_M · 3.5 GB · 20.9 t/s	20.9 tok/s		Q4_K_M · 3.5 GB

#	Model	Speed	Quant · Memory
1	Qwen3.5 4BAlibabaHow to run → Q4_K_M · 3.4 GB · 22.0 t/s	22.0 tok/s	Q4_K_M · 3.4 GB
2	Ling 3.0 TinyInclusion AI Q4_K_M · 5.5 GB · 56.1 t/s	56.1 tok/s	Q4_K_M · 5.5 GB
3	Gemma 4 E2B ITGoogle Q4_K_M · 3.5 GB · 20.9 t/s	20.9 tok/s	Q4_K_M · 3.5 GB
4	Qwen3.5 2BAlibaba Q4_K_M · 1.9 GB · 40.5 t/s	40.5 tok/s	Q4_K_M · 1.9 GB
5	MiniCPM5 2BOpenBMB Q4_K_M · 2.5 GB · 37.7 t/s	37.7 tok/s	Q4_K_M · 2.5 GB

#	Model	Speed ↓	Quant · Memory
1	Qwen3.5 4BAlibabaHow to run → Q4_K_M · 3.4 GB · 22.0 t/s	22.0 tok/s	Q4_K_M · 3.4 GB
2	Ling 3.0 TinyInclusion AI Q4_K_M · 5.5 GB · 56.1 t/s	56.1 tok/s	Q4_K_M · 5.5 GB
3	Qwen3.5 2BAlibaba Q4_K_M · 1.9 GB · 40.5 t/s	40.5 tok/s	Q4_K_M · 1.9 GB
4	MiniCPM5 2BOpenBMB Q4_K_M · 2.5 GB · 37.7 t/s	37.7 tok/s	Q4_K_M · 2.5 GB
5	Gemma 4 E2B ITGoogle Q4_K_M · 3.5 GB · 20.9 t/s	20.9 tok/s	Q4_K_M · 3.5 GB

#	Model	Speed	Quant · Memory
1	Qwen3.5 4BAlibabaHow to run → Q4_K_M · 3.4 GB · 22.0 t/s	22.0 tok/s	Q4_K_M · 3.4 GB
2	Gemma 3 4B ITGoogle Q4_K_M · 5.0 GB · 25.2 t/s	25.2 tok/s	Q4_K_M · 5.0 GB
3	Qwen3.5 9BAlibaba Q4_K_M · 6.6 GB · 11.3 t/s	11.3 tok/s	Q4_K_M · 6.6 GB
4	MiniCPM V 4.7 1BOpenBMB Q4_K_M · 1.6 GB · 56.0 t/s	56.0 tok/s	Q4_K_M · 1.6 GB
5	LFM3 Omni 2BLiquid AI Q4_K_M · 2.4 GB · 42.2 t/s	42.2 tok/s	Q4_K_M · 2.4 GB

See all 281 models on the MacBook Air 13" M3 →Bars = traction for models without a Score yet

About the MacBook Air 13" M3 (16 GB)

The MacBook Air 13" M3 is a 16 GB laptop with more memory than speed: it runs 9B models at 11 tok/s. macOS keeps about 3.5 GB, leaving 12.5 GB for models. Prompt reading is its weak spot: a 4K-token prompt waits 56 s before the first word on Qwen3.5 9B. M3 generation, released 2024; the newer M4 writes 12% faster with 1.0× the compute.

Speed in 16 GB#5102 GB/s

Prompt reading#67 TFLOPS

For models12.5 GBmacOS keeps 3.5 GB

ChipM3released 2024

MacBook Air 13" M3 strengths and weaknesses

Weaknesses

27–31B models don't fit: Qwen3.8 27B needs 17.9 GB at Q4 vs 12.5 GB usable here
Little room for context: Qwen3 14B uses 11.9 of 12.5 GB usable, 0.6 GB left
Slow prompt reading: A 32K-token prompt on Qwen3.5 9B waits 7.5 min for the first token
No CUDA: vLLM, AWQ, GPTQ and FP8 builds don't run; use GGUF or MLX

Memory for models

12.5 GB of 16 GB

9B6.6 GB14B11.9 GB

For models 12.5 GBmacOS keeps 3.5 GBModel size at Q4

27–31B models need 17.9 GB at Q4, more than the 12.5 GB available. The 24 GB config fits Qwen3.8 27B →Or rent an RTX 3090 (24 GB) from $0.19/hr →

Similar devices and alternatives

Other memory sizes of the same machine first, then machines and GPUs people weigh against it, each with the one reason it is worth a look. Speeds on Qwen3.6 35B A3B.

Same chip, 8 GB more memoryMacBook Air 13" M3 (24 GB)Apple · 20.5 GB for models · M3

▼ 33% speed▲ 8 GBno price

Same family 12% faster, same memoryMac Mini M4 (16 GB)Apple · 12.5 GB for models · M4

▲ 12% speedsame memory$799

36% faster, 8 GB more memoryMac Mini M4 Pro (24 GB)Apple · 20.5 GB for models · M4 Pro

▲ 36% speed▲ 8 GB$1,599

Reads prompts 4× faster, 32.5 GB for modelsMac Studio M4 Max (36 GB)Apple · 32.5 GB for models · M4 Max

▲ 4× prompts▲ 62% speed▲ 20 GB$2,499

Reads prompts 53× faster, 24 GB for modelsRTX 4090NVIDIA · 24 GB VRAM · GPU

▲ 53× prompts▲ 344% speed▲ 11.5 GB$1,599rent $0.34/hr

Reads prompts 67× faster, 32 GB for modelsRTX 5090NVIDIA · 32 GB VRAM · GPU

▲ 67× prompts▲ 527% speed▲ 19.5 GB$5,376rent $0.48/hr

MacBook Air 13" M3 tokens per second by model size

Output speed depends on memory bandwidth (102 GB/s). Grey rows need more than the 12.5 GB available.

9BQwen3.5 9B · Q4_K_M · 6.6 GB
11.3tok/s
14BQwen3 14B · Q4_K_M · 11.9 GB tight · Q4_K_M
7.5tok/s
27–31BQwen3.8 27B · not at 4-bit
needs 17.9 GB
35B MoEQwen3.6 35B A3B · not at 4-bit
needs 22.0 GB
70BLlama 3.3 70B Instruct · not at 4-bit
needs 51.3 GB
120B MoEGPT OSS 120B · not at 4-bit
needs 70.8 GB

Estimated speeds: Q4_K_M, 4K context, one user. How we estimate

Chip generations: writing vs compute

M1 → M5

Writing speed (tok/s)Compute (TFLOPS FP16)

Writing speed follows memory bandwidth and barely moved: 24.9 to 44.9 tok/s since the M1. Compute, which sets how fast prompts are read, grew 2.5×. Indexed to the M1; speeds on Qwen3.6 35B A3B, same 16 GB.

All 971 models on the MacBook Air 13" M3

Featured only

Best quant that fits in 12.5 GB, ordered by llmrun Score. Fit grades how well it runs here, S best. How ranking works

LLM models compatible with MacBook Air 13" M3 (16 GB) — ranked by Score, recency and Fit
Model	Quant	VRAM	Speed	Context	Fit
Qwen3Guard Gen 8B8.2BChat Q4_K_M·13.0 t/s	Q4_K_M	7.6 GB61%	13.0 t/s	33K	B52, Decent
GigaChat3 10B A1.8B Base11.5BChat Q4_K_M·38.4 t/s	Q4_K_M	7.7 GB61%	38.4 t/s	262K	A75, Runs well
OLMo 2 0425 1B1.5BChat Q4_K_M·49.1 t/s	Q4_K_M	1.7 GB14%	49.1 t/s	4K	A79, Runs well
Hy MT2 30B A3B30.1BTranslationFunctions IQ2_M·37.7 t/s	IQ2_M	11.3 GB90%	37.7 t/s	262K	B60, Decent
MN 12B Mag Mell R112.2BChatReasoning Q4_K_M·8.9 t/s	Q4_K_M	11.0 GB88%	8.9 t/s	1024K	C36, Usable
Llm Jp 3.1 13B Instruct413.7BChat Q4_K_M·7.0 t/s	Q4_K_M	11.9 GB95%	7.0 t/s	4K	D21, Barely runs
Phi 4 Mini Reasoning3.8BChatMathCodeReasoningFunctions Q4_K_M·25.0 t/s	Q4_K_M	4.8 GB38%	25.0 t/s	131K	A66, Runs well
NeuralDaredevil 8B Abliterated8.0BChat Q4_K_M·13.3 t/s	Q4_K_M	6.2 GB50%	13.3 t/s	8K	B53, Decent
Qwen2.5 Coder 7B Instruct7.6BChatCodeFunctions Q4_K_M·14.4 t/s	Q4_K_M	5.8 GB46%	14.4 t/s	33K	B54, Decent
DeepSeek R1 Distill Qwen 7B7.6BChatReasoningFunctions Q4_K_M·14.4 t/s	Q4_K_M	5.8 GB46%	14.4 t/s	131K	B54, Decent
Qwen2.5 Coder 14B Instruct14.8BChatCodeFunctions Q4_K_M·7.5 t/s	Q4_K_M	12.4 GB99%	7.5 t/s	33K	D15, Barely runs
SmolLM3 3B Base3.1BChat Q4_K_M·31.2 t/s	Q4_K_M	3.4 GB27%	31.2 t/s	66K	A71, Runs well
TinyLlama 1.1B Chat V0.61.1BChat Q4_K_M·71.0 t/s	Q4_K_M	1.0 GB8%	71.0 t/s	2K	S86, Runs great
BharatGPT 3B Indic3.2BChat BF16·10.1 t/s	BF16	9.1 GB72%	10.1 t/s	—	B48, Decent
L3 8B Stheno V3.28.0BChat Q4_K_M·13.3 t/s	Q4_K_M	6.2 GB50%	13.3 t/s	8K	B53, Decent

MacBook Air 13" M3 specs

Specs

Chip: M3
CPU cores: 8
GPU cores: 10
Unified memory: 16 GB
For models: 12.5 GB (macOS keeps 3.5 GB)
Memory bandwidth: 102.4 GB/s
FP16 (dense): 7 TFLOPS
Neural Engine: 18 TOPS
Released: 2024-03-08

MacBook Air 13" M3 FAQ

How much memory is available for AI on the MacBook Air 13" M3 (16 GB)?

About 12.5 GB of the 16 GB. macOS keeps roughly 3.5 GB for itself and other apps.

What is the largest model the MacBook Air 13" M3 (16 GB) can run?

GPT OSS 20B (20.9B) is the largest at 4-bit or better: at Q4_K_S it uses 12.4 GB, 99% of the available memory, and runs at about 25.8 tok/s.

Can the MacBook Air 13" M3 (16 GB) run Qwen3.5 9B?

Yes. Qwen3.5 9B fits at Q4_K_M, using 6.6 GB of the 12.5 GB available, and it is the best model that runs well on this machine.

Can the MacBook Air 13" M3 (16 GB) run 27–31B models?

No. Qwen3.8 27B needs 17.9 GB at Q4, more than the 12.5 GB available.

How long does the MacBook Air 13" M3 (16 GB) take to read a long prompt?

On Qwen3.5 9B, about 56 s for a 4K-token prompt and 7.5 min for a 32K-token document before the first word appears.

Is renting a GPU cheaper than buying the MacBook Air 13" M3?

An RTX 3090 (24 GB) rents from $0.12/hr.

12 GB GPUs All Macs Laptops Mac Mini M2 Pro MacBook Pro 14" M1 Pro MacBook Pro 14" M2 Pro MacBook Pro 16" M1 Pro MacBook Pro 16" M2 Pro MacBook Air 13" M5 MacBook Pro 14" M3 Pro Best coding LLMs All hardware