Apple · M1 Pro · Laptop

Best AI Models for MacBook Pro 14" M1 Pro (16 GB)

Runs 9B models well; 14B only just fits in 12.5 GB, and 27–31B doesn't fit.

16 GB unified12.5 GB for models200 GB/s9 TFLOPS FP162021

Memory

Same chip in

What LLMs can the MacBook Pro 14" M1 Pro run?

#	Model	Speed	Quant · Memory
1	Qwen3.5 9BAlibabaHow to run → Q4_K_M · 6.6 GB	22.0 tok/s	Q4_K_M · 6.6 GB
2	Qwen3 8BAlibaba Q4_K_M · 7.6 GB	25.4 tok/s	Q4_K_M · 7.6 GB
3	Gemma 3 12B ITGoogle Q4_K_M · 10.9 GB	17.4 tok/s	Q4_K_M · 10.9 GB
4	Mistral Nemo Instruct 2407Mistral AI Q4_K_M · 11.0 GB	17.3 tok/s	Q4_K_M · 11.0 GB
5	Gemma 4 12B ITGoogle Q4_K_M · 9.0 GB	17.0 tok/s	Q4_K_M · 9.0 GB

#	Model	Speed	Coding Score	Quant · Memory
1	Llama 3.1 8B InstructMetaHow to run → Q4_K_M · 7.9 GB	26.4 tok/s		Q4_K_M · 7.9 GB
2	Qwen3.5 9BAlibaba Q4_K_M · 6.6 GB	22.0 tok/s	overall	Q4_K_M · 6.6 GB
3	Qwen3 8BAlibaba Q4_K_M · 7.6 GB	25.4 tok/s	overall	Q4_K_M · 7.6 GB
4	Gemma 4 12B ITGoogle Q4_K_M · 9.0 GB	17.0 tok/s		Q4_K_M · 9.0 GB
5	Gemma 4 E4B ITGoogle Q4_K_M · 5.6 GB	26.3 tok/s		Q4_K_M · 5.6 GB

#	Model	Speed	Quant · Memory
1	Qwen3.5 9BAlibabaHow to run → Q4_K_M · 6.6 GB	22.0 tok/s	Q4_K_M · 6.6 GB
2	Qwen3 8BAlibaba Q4_K_M · 7.6 GB	25.4 tok/s	Q4_K_M · 7.6 GB
3	Llama 3.1 8B InstructMeta Q4_K_M · 7.9 GB	26.4 tok/s	Q4_K_M · 7.9 GB
4	Gemma 3 4B ITGoogle Q4_K_M · 5.0 GB	49.3 tok/s	Q4_K_M · 5.0 GB
5	Gemma 4 12B ITGoogle Q4_K_M · 9.0 GB	17.0 tok/s	Q4_K_M · 9.0 GB

#	Model	Speed	Quant · Memory
1	Qwen3.5 9BAlibabaHow to run → Q4_K_M · 6.6 GB	22.0 tok/s	Q4_K_M · 6.6 GB
2	Llama 3.1 8B InstructMeta Q4_K_M · 7.9 GB	26.4 tok/s	Q4_K_M · 7.9 GB
3	Llama 3.2 1B InstructMeta Q4_K_M · 2.3 GB	171 tok/s	Q4_K_M · 2.3 GB
4	Mistral Nemo Instruct 2407Mistral AI Q4_K_M · 11.0 GB	17.3 tok/s	Q4_K_M · 11.0 GB
5	Qwen3.5 4BAlibaba Q4_K_M · 3.4 GB	42.9 tok/s	Q4_K_M · 3.4 GB

#	Model	Speed ↓	Quant · Memory
1	Qwen3.5 9BAlibabaHow to run → Q4_K_M · 6.6 GB	22.0 tok/s	Q4_K_M · 6.6 GB
2	Ling 3.0 TinyInclusion AI Q4_K_M · 5.5 GB	87.1 tok/s	Q4_K_M · 5.5 GB
3	Gemma 4 E4B ITGoogle Q4_K_M · 5.6 GB	26.3 tok/s	Q4_K_M · 5.6 GB
4	Qwen3 8BAlibaba Q4_K_M · 7.6 GB	25.4 tok/s	Q4_K_M · 7.6 GB
5	Gemma 4 12B ITGoogle Q4_K_M · 9.0 GB	17.0 tok/s	Q4_K_M · 9.0 GB

#	Model	Speed	Quant · Memory
1	Qwen3.5 9BAlibabaHow to run → Q4_K_M · 6.6 GB	22.0 tok/s	Q4_K_M · 6.6 GB
2	Gemma 3 12B ITGoogle Q4_K_M · 10.9 GB	17.4 tok/s	Q4_K_M · 10.9 GB
3	Gemma 3 4B ITGoogle Q4_K_M · 5.0 GB	49.3 tok/s	Q4_K_M · 5.0 GB
4	Qwen3.5 4BAlibaba Q4_K_M · 3.4 GB	42.9 tok/s	Q4_K_M · 3.4 GB
5	MiMo V2.6 Distill Qwen 9BXiaomi Q4_K_M · 6.5 GB	22.5 tok/s	Q4_K_M · 6.5 GB

See all 257 models on the MacBook Pro 14" M1 Pro →Bars = traction for models without a Score yet
Task rankings use that task's benchmarks, topped up from Overall when short; bars mark well-known models with no Score yet.

About the MacBook Pro 14" M1 Pro (16 GB)

The MacBook Pro 14" M1 Pro is the fastest 16 GB machine: it runs 9B models well. macOS keeps about 3.5 GB, leaving 12.5 GB for models. Prompt reading is its weak spot: a 4K-token prompt waits 43 s before the first word on Qwen3.5 9B. M1 Pro generation, released 2021; the newer M2 Pro writes 0% faster with 1.3× the compute.

Speed in 16 GB#1200 GB/s

Prompt reading#49 TFLOPS

For models12.5 GBmacOS keeps 3.5 GB

ChipM1 Proreleased 2021

MacBook Pro 14" M1 Pro strengths and weaknesses

Strengths

Runs 7–9B models: Qwen3.5 9B at 22.0 tok/s in 6.6 GB

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 5.8 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 32 GB config fits Qwen3.8 27B →

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, 2× the memoryMacBook Pro 14" M1 Pro (32 GB)Apple · 28.5 GB for models · M1 Pro

same speed▲ 16 GBno price

Same family Newer machine, 40% slowerMac Mini M4 (16 GB)Apple · 12.5 GB for models · M4

▼ 40% 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

105% faster, 20 GB more memoryMac Studio M4 Max (36 GB)Apple · 32.5 GB for models · M4 Max

▲ 105% speed▲ 20 GB$2,499

Reads prompts 41× faster, 24 GB for modelsRTX 4090NVIDIA · 24 GB VRAM · GPU

▲ 41× prompts▲ 368% speed▲ 11.5 GB$1,599rent $0.34/hr

Reads prompts 52× faster, 32 GB for modelsRTX 5090NVIDIA · 32 GB VRAM · GPU

▲ 52× prompts▲ 732% speed▲ 19.5 GB$5,376rent $0.64/hr

MacBook Pro 14" M1 Pro tokens per second by model size

Output speed depends on memory bandwidth (200 GB/s). Grey rows need more than the 12.5 GB available.

9BQwen3.5 9B · Q4_K_M · 6.6 GB
22.0tok/s
14BQwen3 14B · Q4_K_M · 11.9 GB tight · Q4_K_M
14.7tok/s
27–31BQwen3.8 27B · does not fit
needs 17.9 GB
35B MoEQwen3.6 35B A3B · does not fit
needs 22.0 GB
70BLlama 3.3 70B Instruct · does not fit
needs 51.3 GB
120B MoEGPT OSS 120B · does not fit
needs 70.8 GB

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

Pro generations: writing vs compute

M1 Pro → M5 Pro

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

Writing speed follows memory bandwidth and barely moved: 22.0 to 33.8 tok/s since the M1 Pro. Compute, which sets how fast prompts are read, grew 2.8×. Indexed to the M1 Pro; speeds on Qwen3.5 9B, same 16 GB.

All 257 models on the MacBook Pro 14" M1 Pro

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 Pro 14" M1 Pro (16 GB) — ranked by Score, recency and Fit
Model	Quant	VRAM	Speed	Context	Fit
Qwen3.5 9B9.7BVisionFunctions 9.7B·Q4_K_M·22.0 t/s·262K ctx	Q4_K_M	6.6 GB53%	22.0 t/s	262K	B62, Decent
Qwen3.5 4B4.7BVisionFunctions 4.7B·Q4_K_M·42.9 t/s·262K ctx	Q4_K_M	3.4 GB27%	42.9 t/s	262K	A77, Runs well
Qwen3.8 27B27.8BVisionFunctions 27.8B·IQ3_XXS·12.2 t/s·262K ctx	IQ3_XXS	12.0 GB96%	12.2 t/s	262K	D26, Barely runs
Gemma 4 12B IT12.0BChatFunctions 12.0B·Q4_K_M·17.0 t/s·262K ctx	Q4_K_M	9.0 GB72%	17.0 t/s	262K	B56, Decent
Gemma 4 E4B IT8.0BChatFunctions 8.0B·Q4_K_M·26.3 t/s·131K ctx	Q4_K_M	5.6 GB44%	26.3 t/s	131K	A67, Runs well
Ling 3.0 Tiny7.9BChatFunctions 7.9B·Q4_K_M·87.1 t/s·131K ctx	Q4_K_M	5.5 GB44%	87.1 t/s	131K	S89, Runs great
MiniCPM5 2B2.5BChatFunctions 2.5B·Q4_K_M·73.7 t/s·131K ctx	Q4_K_M	2.5 GB20%	73.7 t/s	131K	S86, Runs great
LFM2.5 8B A1B8.5BChatFunctions 8.5B·Q4_K_M·79.4 t/s·128K ctx	Q4_K_M	5.6 GB45%	79.4 t/s	128K	S87, Runs great
Ornith 1.0 9B9.4BChatFunctions 9.4B·Q4_K_M·22.5 t/s·262K ctx	Q4_K_M	6.5 GB52%	22.5 t/s	262K	B63, Decent
MiMo V2.6 Distill Qwen 9B9.4BVisionCodeFunctions 9.4B·Q4_K_M·22.5 t/s·262K ctx	Q4_K_M	6.5 GB52%	22.5 t/s	262K	B63, Decent
Apertus V1.5 8B8.9BVision 8.9B·Q4_K_M·23.8 t/s	Q4_K_M	8.5 GB68%	23.8 t/s	—	B64, Decent
Gemma 4 26B A4B IT25.8BVisionFunctions 25.8B·Q3_K_S·48.7 t/s·262K ctx	Q3_K_S	12.3 GB98%	48.7 t/s	262K	C44, Usable
MinerU2.5 Pro 2605 1.2B1.2BVision 1.2B·Q4_K_M·137.3 t/s·8K ctx	Q4_K_M	1.1 GB9%	137.3 t/s	8K	S96, Runs great
MiniCPM O 4 59.4BChatFunctions 9.4B·Q4_K_M·22.5 t/s·41K ctx	Q4_K_M	8.3 GB67%	22.5 t/s	41K	B63, Decent
ZAYA1 VL 8B9.7BVision 9.7B·Q4_K_M·89.0 t/s·33K ctx	Q4_K_M	7.5 GB60%	89.0 t/s	33K	S89, Runs great

MacBook Pro 14" M1 Pro specs

Specs

Chip: M1 Pro
CPU cores: 8
GPU cores: 14
Unified memory: 16 GB
For models: 12.5 GB (macOS keeps 3.5 GB)
Memory bandwidth: 200 GB/s
FP16 (dense): 9.1 TFLOPS
Neural Engine: 11 TOPS
Released: 2021-10-26

MacBook Pro 14" M1 Pro FAQ

How much memory is available for AI on the MacBook Pro 14" M1 Pro (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 Pro 14" M1 Pro (16 GB) can run?

GPT OSS 20B (20.9B) at Q4_K_S uses 12.4 GB, 99% of the available memory, and runs at about 45.1 tok/s.

Can the MacBook Pro 14" M1 Pro (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 Pro 14" M1 Pro (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 Pro 14" M1 Pro (16 GB) take to read a long prompt?

On Qwen3.5 9B, about 43 s for a 4K-token prompt and 5.8 min for a 32K-token document before the first word appears.

Is renting a GPU cheaper than buying the MacBook Pro 14" M1 Pro?

A Tesla V100 (16 GB) rents from $0.10/hr.

12 GB GPUs All Macs Laptops Mac Mini M2 Pro MacBook Pro 14" M2 Pro MacBook Pro 16" M2 Pro MacBook Air 13" M5 MacBook Air 15" M5 Best coding LLMs All hardware