Apple · M3 · Laptop

Best AI Models for MacBook Air 13" M3 (8 GB)

Runs only small models; 9B doesn't fit in 4.5 GB.

8 GB unified4.5 GB for models102.4 GB/s6 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 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 4 E2B ITGoogle Q4_K_M · 3.5 GB · 20.9 t/s	20.9 tok/s	Q4_K_M · 3.5 GB
3	MiniCPM5 2BOpenBMB Q4_K_M · 2.5 GB · 37.7 t/s	37.7 tok/s	Q4_K_M · 2.5 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	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

#	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	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
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	Qwen3.5 2BAlibaba Q4_K_M · 1.9 GB · 40.5 t/s	40.5 tok/s	Q4_K_M · 1.9 GB
3	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
4	LFM3 Omni 2BLiquid AI Q4_K_M · 2.4 GB · 42.2 t/s	42.2 tok/s	Q4_K_M · 2.4 GB
5	Cosmos Reason2 2BNVIDIA Q4_K_M · 3.5 GB · 44.5 t/s	44.5 tok/s	Q4_K_M · 3.5 GB

See all 160 models on the MacBook Air 13" M3 →Bars = traction for models without a Score yet

About the MacBook Air 13" M3 (8 GB)

The MacBook Air 13" M3 is the fastest 8 GB machine: it runs only small models. macOS keeps about 3.5 GB, leaving 4.5 GB for models. With 6 TFLOPS it reads long prompts faster than most 8 GB machines: a 4K-token prompt takes 34 s. M3 generation, released 2024; the newer M4 writes -29% faster with 1.2× the compute.

Speed in 8 GB#1102 GB/s

Prompt reading#26 TFLOPS

For models4.5 GBmacOS keeps 3.5 GB

ChipM3released 2024

MacBook Air 13" M3 strengths and weaknesses

Weaknesses

7–9B models don't fit: Qwen3.5 9B needs 6.6 GB at Q4 vs 4.5 GB usable here
Slow prompt reading: A 32K-token prompt on Qwen3.5 4B waits 4.5 min for the first token
No CUDA: vLLM, AWQ, GPTQ and FP8 builds don't run; use GGUF or MLX

Memory for models

4.5 GB of 8 GB

4B3.4 GB

For models 4.5 GBmacOS keeps 3.5 GBModel size at Q4

9B models need 6.6 GB at Q4, more than the 4.5 GB available. The 16 GB config fits Qwen3.5 9B →Or rent an RTX 3080 Ti (12 GB) from $0.12/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 Qwen3.5 9B.

Same chip, 3× the memoryMacBook Air 13" M3 (16 GB)Apple · 12.5 GB for models · M3

▼ 40% speed▲ 8 GBno price

Same family Same chip, 5× the memoryMacBook Air 13" M3 (24 GB)Apple · 20.5 GB for models · M3

▼ 40% speed▲ 16 GBno price

Same family Reads prompts 3× faster, 20.5 GB for modelsMac Mini M4 Pro (24 GB)Apple · 20.5 GB for models · M4 Pro

▲ 3× prompts▲ 60% speed▲ 16 GB$1,599

Reads prompts 5× faster, 32.5 GB for modelsMac Studio M4 Max (36 GB)Apple · 32.5 GB for models · M4 Max

▲ 5× prompts▲ 141% speed▲ 28 GB$2,499

Reads prompts 66× faster, 24 GB for modelsRTX 4090NVIDIA · 24 GB VRAM · GPU

▲ 66× prompts▲ 451% speed▲ 19.5 GB$1,599rent $0.34/hr

Reads prompts 84× faster, 32 GB for modelsRTX 5090NVIDIA · 32 GB VRAM · GPU

▲ 84× prompts▲ 879% speed▲ 27.5 GB$5,376rent $0.50/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 4.5 GB available.

9BQwen3.5 9B · not at 4-bit
needs 6.6 GB
14BQwen3 14B · not at 4-bit
needs 11.9 GB
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: 12.5 to 16.9 tok/s since the M1. Compute, which sets how fast prompts are read, grew 2.8×. Indexed to the M1; speeds on Qwen3.5 9B, same 8 GB.

All 586 models on the MacBook Air 13" M3

Featured only

Best quant that fits in 4.5 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 (8 GB) — ranked by Score, recency and Fit
Model	Quant	VRAM	Speed	Context	Fit
Qwen3.5 4B4.7BVisionFunctions Q4_K_M·22.0 t/s	Q4_K_M	3.4 GB76%	22.0 t/s	262K	B62, Decent
Gemma 4 E2B IT5.1BChatFunctions Q4_K_M·20.9 t/s	Q4_K_M	3.5 GB78%	20.9 t/s	131K	B61, Decent
MiniCPM5 2B2.5BChatFunctions Q4_K_M·37.7 t/s	Q4_K_M	2.5 GB56%	37.7 t/s	131K	A74, Runs well
Qwen3.5 2B2.3BVisionFunctions Q4_K_M·40.5 t/s	Q4_K_M	1.9 GB42%	40.5 t/s	262K	A75, Runs well
Unlimited OCR3.3BVision Q4_K_M·71.5 t/s	Q4_K_M	3.3 GB74%	71.5 t/s	33K	S86, Runs great
MiniCPM V 4.7 1B1.6BVisionFunctions Q4_K_M·56.0 t/s	Q4_K_M	1.6 GB36%	56.0 t/s	262K	A82, Runs well
LFM3 1.7B1.7BChatFunctions Q4_K_M·49.8 t/s	Q4_K_M	2.1 GB48%	49.8 t/s	262K	A79, Runs well
LFM3 Omni 2B2.2BVisionChatFunctions Q4_K_M·42.2 t/s	Q4_K_M	2.4 GB53%	42.2 t/s	128K	A76, Runs well
LFM3 VL 2B1.9BVisionChatFunctions Q4_K_M·46.2 t/s	Q4_K_M	2.3 GB50%	46.2 t/s	128K	A78, Runs well
D1 Omni 600M587MVision Q4_K_M·99.6 t/s	Q4_K_M	1.2 GB26%	99.6 t/s	128K	S91, Runs great
MiniCPM V 4.61.3BVisionFunctions Q4_K_M·63.4 t/s	Q4_K_M	1.5 GB33%	63.4 t/s	262K	A84, Runs well
D1 2B1.9BVisionFunctions Q4_K_M·46.2 t/s	Q4_K_M	2.3 GB50%	46.2 t/s	128K	A78, Runs well
MinerU2.5 Pro 2605 1.2B1.2BVision Q4_K_M·70.3 t/s	Q4_K_M	1.1 GB24%	70.3 t/s	8K	S86, Runs great
MiniCPM5 2B DSpark324MChat Q4_K_M·143.4 t/s	Q4_K_M	0.6 GB13%	143.4 t/s	131K	S96, Runs great
D1 3B3.1BVisionFunctions Q4_K_M·31.2 t/s	Q4_K_M	2.6 GB57%	31.2 t/s	33K	A71, Runs well

MacBook Air 13" M3 specs

Specs

Chip: M3
CPU cores: 8
GPU cores: 8
Unified memory: 8 GB
For models: 4.5 GB (macOS keeps 3.5 GB)
Memory bandwidth: 102.4 GB/s
FP16 (dense): 5.6 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 (8 GB)?

About 4.5 GB of the 8 GB. macOS keeps roughly 3.5 GB for itself and other apps.

What is the largest model the MacBook Air 13" M3 (8 GB) can run?

Qwen3.5 4B (4.7B) is the largest at 4-bit or better: at Q4_K_M it uses 3.4 GB, 76% of the available memory, and runs at about 22.0 tok/s.

Can the MacBook Air 13" M3 (8 GB) run 9B models?

No. Qwen3.5 9B needs 6.6 GB at Q4, more than the 4.5 GB available.

How long does the MacBook Air 13" M3 (8 GB) take to read a long prompt?

On Qwen3.5 4B, about 34 s for a 4K-token prompt and 4.5 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 3080 Ti (12 GB) rents from $0.08/hr.

8 GB GPUs All Macs Laptops Jetson Orin Nano 8GB Super Mac Mini M2 MacBook Air 13" M2 iPhone 17 Pro Max Best coding LLMs All hardware