Apple · M5 · Laptop

Best AI Models for MacBook Pro 14-inch (M5) (32 GB)

Runs 9B and 35B MoE models well; 14B and 27–31B fit but are slow (11 and 6 tok/s), and 70B doesn't fit in 28.5 GB.

32 GB unified28.5 GB for models153.6 GB/s16 TFLOPS FP162025

Same chip in

MacBook Pro 14-inch$1,839 MacBook Air 13"MacBook Air 15"iPad Pro 13"MacBook Pro 14"

What LLMs can the MacBook Pro 14-inch (M5) run?

#	Model	Speed	Quant · Memory
1	Qwen3.6 35B A3BAlibabaHow to run → Q4_K_M · 22.0 GB · 28.6 t/s	28.6 tok/s	Q4_K_M · 22.0 GB
2	Gemma 4 26B A4B ITGoogle Q4_K_M · 16.5 GB · 31.7 t/s	31.7 tok/s	Q4_K_M · 16.5 GB
3	Qwen3 30B A3B Thinking 2507Alibaba Q4_K_M · 19.4 GB · 34.8 t/s	34.8 tok/s	Q4_K_M · 19.4 GB
4	GPT OSS 20BOpenAI Q4_K_M · 13.1 GB · 34.6 t/s	34.6 tok/s	Q4_K_M · 13.1 GB
5	NVIDIA Nemotron 3.5 Lightning 30B A3B BF16NVIDIA Q4_K_M · 19.3 GB · 41.9 t/s	41.9 tok/s	Q4_K_M · 19.3 GB

#	Model	Speed	Quant · Memory
1	Qwen3.6 35B A3BAlibabaHow to run → Q4_K_M · 22.0 GB · 28.6 t/s	28.6 tok/s	Q4_K_M · 22.0 GB
2	Gemma 4 26B A4B ITGoogle Q4_K_M · 16.5 GB · 31.7 t/s	31.7 tok/s	Q4_K_M · 16.5 GB
3	GPT OSS 20BOpenAI Q4_K_M · 13.1 GB · 34.6 t/s	34.6 tok/s	Q4_K_M · 13.1 GB
4	Llama 3.1 8B InstructMeta Q4_K_M · 7.9 GB · 20.3 t/s	20.3 tok/s	Q4_K_M · 7.9 GB
5	NVIDIA Nemotron 3.5 Lightning 30B A3B BF16NVIDIA Q4_K_M · 19.3 GB · 41.9 t/s	41.9 tok/s	Q4_K_M · 19.3 GB

#	Model	Speed	Quant · Memory
1	Qwen3.6 35B A3BAlibabaHow to run → Q4_K_M · 22.0 GB · 28.6 t/s	28.6 tok/s	Q4_K_M · 22.0 GB
2	Gemma 4 26B A4B ITGoogle Q4_K_M · 16.5 GB · 31.7 t/s	31.7 tok/s	Q4_K_M · 16.5 GB
3	Qwen3.5 9BAlibaba Q4_K_M · 6.6 GB · 16.9 t/s	16.9 tok/s	Q4_K_M · 6.6 GB
4	GPT OSS 20BOpenAI Q4_K_M · 13.1 GB · 34.6 t/s	34.6 tok/s	Q4_K_M · 13.1 GB
5	NVIDIA Nemotron 3.5 Lightning 30B A3B BF16NVIDIA Q4_K_M · 19.3 GB · 41.9 t/s	41.9 tok/s	Q4_K_M · 19.3 GB

#	Model	Speed	Quant · Memory
1	Gemma 4 26B A4B ITGoogleHow to run → Q4_K_M · 16.5 GB · 31.7 t/s	31.7 tok/s	Q4_K_M · 16.5 GB
2	Qwen3 30B A3B Thinking 2507Alibaba Q4_K_M · 19.4 GB · 34.8 t/s	34.8 tok/s	Q4_K_M · 19.4 GB
3	Qwen3.5 9BAlibaba Q4_K_M · 6.6 GB · 16.9 t/s	16.9 tok/s	Q4_K_M · 6.6 GB
4	GPT OSS 20BOpenAI Q4_K_M · 13.1 GB · 34.6 t/s	34.6 tok/s	Q4_K_M · 13.1 GB
5	NVIDIA Nemotron 3.5 Lightning 30B A3B BF16NVIDIA Q4_K_M · 19.3 GB · 41.9 t/s	41.9 tok/s	Q4_K_M · 19.3 GB

#	Model	Speed ↓	Quant · Memory
1	Qwen3 30B A3B Thinking 2507AlibabaHow to run → Q4_K_M · 19.4 GB · 34.8 t/s	34.8 tok/s	Q4_K_M · 19.4 GB
2	NVIDIA Nemotron 3.5 Lightning 30B A3B BF16NVIDIA Q4_K_M · 19.3 GB · 41.9 t/s	41.9 tok/s	Q4_K_M · 19.3 GB
3	Qwen3 30B A3B Instruct 2507Alibaba Q4_K_M · 19.4 GB · 34.8 t/s	34.8 tok/s	Q4_K_M · 19.4 GB
4	GPT OSS 20BOpenAI Q4_K_M · 13.1 GB · 34.6 t/s	34.6 tok/s	Q4_K_M · 13.1 GB
5	Gemma 4 26B A4B ITGoogle Q4_K_M · 16.5 GB · 31.7 t/s	31.7 tok/s	Q4_K_M · 16.5 GB

See all 341 models on the MacBook Pro 14-inch (M5) →Bars = traction for models without a Score yet

About the MacBook Pro 14-inch (M5)

The MacBook Pro 14-inch (M5) is a 32 GB laptop with more memory than speed: it runs 9B and 35B MoE models well. macOS keeps about 3.5 GB, leaving 28.5 GB for models. Prompt reading is its weak spot: a 4K-token prompt waits 12 s before the first word on Qwen3.6 35B A3B. At ≈$1,839 it gives 15.6 tok/s per $1,000, 6th of the 6 machines compared here. M5 generation, released 2025.

Speed in 32 GB#6154 GB/s

Prompt reading#516 TFLOPS

For models28.5 GBmacOS keeps 3.5 GB

ChipM5released 2025

MacBook Pro 14-inch (M5) strengths and weaknesses

Strengths

Runs 35B MoE models: Qwen3.6 35B A3B at 28.6 tok/s in 22 GB

Weaknesses

70B models don't fit: Llama 3.3 70B Instruct needs 51.3 GB at Q4 vs 28.5 GB usable here
Slow on large dense models: Qwen3.8 27B at 6.2 tok/s
Slow prompt reading: A 32K-token prompt on Qwen3.6 35B A3B waits 1.6 min for the first token
No CUDA: vLLM, AWQ, GPTQ and FP8 builds don't run; use GGUF or MLX

Memory for models

28.5 GB of 32 GB

9B6.6 GB14B11.9 GB27–31B17.9 GB35B MoE22 GB

9B6.6 GB14B11.9 GB35B MoE22 GB

For models 28.5 GBmacOS keeps 3.5 GBModel size at Q4

70B models need 51.3 GB at Q4, more than the 28.5 GB available.Or rent an A100 (80 GB) from $1.24/hr →

Speed per dollar and per watt

NewUsed

On Qwen3.6 35B A3B (35B params, 3B active) at Q4_K_M. New means a shop price, either a street quote or the maker's own price; used is compared with used. The last two columns are the speed you get per $1,000 of price and per 100 W of power; higher is better.

Machine	New price	tok/s	tok/s per $1,000	tok/s per 100 W
RTX 509032 GBBest new value	about $5,376	213	39.7	37.1
Mac Mini M4 Pro24 GB	about $1,599	46.3	29.0	33.1
Mac Mini M432 GB	about $999	23.5	23.5	36.2
Mac Studio M4 Max36 GB	about $2,499	55.2	22.1	38.1
MacBook Pro 14 M5 Pro64 GB	about $2,299	46.5	20.2	–
MacBook Pro 14 M532 GB	about $1,839	28.6	15.6	–

Machine	Used price	tok/s	tok/s per $1,000	tok/s per 100 W
RTX 409024 GBBest used value	about $3,000	151	50.3	33.6
RTX 509032 GB	about $6,400	213	33.3	37.1
Mac Studio M4 Max36 GB	about $2,000	55.2	27.6	38.1
MacBook Pro 14 M5 Pro64 GB	about $2,109	46.5	22.0	–

Cost per token: the MacBook Pro 14-inch (M5) against 24–64 GB machines and GPUs

On Qwen3.6 35B A3B (35B params, 3B active, Q4_K_M, 4K context). Speed, cost per token and power per token depend on the model.

NewUsed

Speed$ per 1M tokens

24–36 GB48–64 GBthis laptopat MSRP

Cost per 1M output tokenson Qwen3.6 35B A3B · card over 3 years + power

$4.08

Machine, new price: $4.08
Power: not published

3-year cost of ownership$1,839

Or rent an A100 in the cloud$0.40/hr

Renting costs as much as buying after ≈4,600 hours (≈3.1 years at 4 h a day).

Power$/kWhUseh/dayKeepyears

Each dot is a machine or GPU; hover or tap it for its numbers, click to open it. Machines without a price for the chosen basis are left out. Machines without a published power figure are left out of Per watt and costed without power. How we calculate cost per token

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.

Machine, 18% slowerMac Mini M4 (32 GB)Apple · 28.5 GB for models · M4

▼ 18% speedsame memory$999

93% faster, 4 GB more memoryMac Studio M4 Max (36 GB)Apple · 32.5 GB for models · M4 Max

▲ 93% speed▲ 4 GB$2,499

Machine, 62% fasterMac Mini M4 Pro (24 GB)Apple · 20.5 GB for models · M4 Pro

▲ 62% speed▼ 8 GB$1,599

32 GB more, 63% faster for $460 moreMacBook Pro 14 M5 ProApple · 60.5 GB for models · M5 Pro

▲ 63% speed▲ $460 more▲ 32 GB$2,299

Reads prompts 23× faster, 24 GB for modelsRTX 4090NVIDIA · 24 GB VRAM · GPU

▲ 23× prompts▲ 428% speed▼ 4.5 GB$1,599rent $0.37/hr

Reads prompts 30× faster, 32 GB for modelsRTX 5090NVIDIA · 32 GB VRAM · GPU

▲ 30× prompts▲ 646% speed▲ $3,537 more▲ 3.5 GB$5,376rent $0.50/hr

MacBook Pro 14-inch (M5) tokens per second by model size

Output speed depends on memory bandwidth (154 GB/s). Grey rows need more than the 28.5 GB available.

9BQwen3.5 9B · Q4_K_M · 6.6 GB
16.9tok/s
14BQwen3 14B · Q4_K_M · 11.9 GB
11.3tok/s
27–31BQwen3.8 27B · Q4_K_M · 17.9 GB slow
6.2tok/s
35B MoEQwen3.6 35B A3B · Q4_K_M · 22.0 GB
28.6tok/s
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 28.6 tok/s since the M1. Compute, which sets how fast prompts are read, grew 3.1×. Indexed to the M1; speeds on Qwen3.6 35B A3B, same 16 GB.

All 1165 models on the MacBook Pro 14-inch (M5)

Featured only

Best quant that fits in 28.5 GB, ordered by llmrun Score. Fit grades how well it runs here, S best. How ranking works

LLM models compatible with MacBook Pro 14-inch (M5) — ranked by Score, recency and Fit
Model	Quant	VRAM	Speed	Context	Fit
KONI Llama3.1 8B Instruct 202410248.0BChatFunctions Q4_K_M·19.9 t/s	Q4_K_M	7.3 GB26%	19.9 t/s	131K	B60, Decent
Saiga Llama3 8B8.0BChat Q4_K_M·19.9 t/s	Q4_K_M	6.2 GB22%	19.9 t/s	8K	B60, Decent
Granite 3.3 2B Instruct2.5BChatFunctions Q4_K_M·54.0 t/s	Q4_K_M	3.2 GB11%	54.0 t/s	131K	A81, Runs well
TinyLlama 1.1B Intermediate Step 1431k 3T1.1BChat Q4_K_M·106.5 t/s	Q4_K_M	1.0 GB4%	106.5 t/s	2K	S92, Runs great
Chadrock 35B Ace Saber Rocmfp4 Mtp35BChat Q4_K_M·4.7 t/s	Q4_K_M	27.0 GB95%	4.7 t/s	—	D18, Barely runs
Aya Expanse 32B32.3BChat Q4_K_M·5.0 t/s	Q4_K_M	25.1 GB88%	5.0 t/s	—	C31, Usable
Yi 1.5 34B Chat34.4BChat Q4_K_M·5.0 t/s	Q4_K_M	21.9 GB77%	5.0 t/s	4K	C42, Usable
GOT OCR2 0716MVision Q4_K_M·115.6 t/s	Q4_K_M	2.3 GB8%	115.6 t/s	33K	S94, Runs great
VLM2Vec Full4.1BChat BF16·11.4 t/s	BF16	15.0 GB53%	11.4 t/s	131K	B50, Decent
Shieldgemma 9B9.2BChat Q4_K_M·17.6 t/s	Q4_K_M	8.8 GB31%	17.6 t/s	—	B57, Decent
DeepSeek R1 Distill Qwen 14B Abliterated v214.8BChatReasoning Q4_K_M·11.2 t/s	Q4_K_M	12.4 GB43%	11.2 t/s	131K	B49, Decent
PLLuM 12B Chat12.2BChat Q4_K_M·13.3 t/s	Q4_K_M	11.0 GB39%	13.3 t/s	131K	B53, Decent
Qwen Base Invoicev1.01 1.5B1.5BChat Q4_K_M·84.0 t/s	Q4_K_M	1.7 GB6%	84.0 t/s	33K	S88, Runs great
Olmo 3 7B Instruct7.3BChatFunctions Q4_K_M·18.7 t/s	Q4_K_M	8.4 GB30%	18.7 t/s	66K	B58, Decent
Codegen 350M Mono350MChatCode FP16·139.6 t/s	FP16	0.8 GB3%	139.6 t/s	2K	S96, Runs great

MacBook Pro 14-inch (M5) specs

Specs

Chip: M5
CPU cores: 10
GPU cores: 10
Unified memory: 32 GB LPDDR5X
For models: 28.5 GB (macOS keeps 3.5 GB)
Memory bandwidth: 153.6 GB/s
FP16 (dense): 16 TFLOPS
Neural Engine: 38 TOPS
NPU: 16-core Neural Engine
Size: MacBook Pro 14-inch
Released: 2025-10-22
MSRP: $1,599

MacBook Pro 14-inch (M5) FAQ

Is the MacBook Pro 14-inch (M5) worth it for local LLMs in 2026?

At ≈$1,839 it gives 15.6 tok/s per $1,000 on Qwen3.6 35B A3B, 6th of the 6 machines compared here. It runs 9B and 35B MoE models well; 14B and 27–31B fit but are slow (11 and 6 tok/s), and 70B doesn't fit in 28.5 GB.

How much memory is available for AI on the MacBook Pro 14-inch (M5)?

About 28.5 GB of the 32 GB. macOS keeps roughly 3.5 GB for itself and other apps.

What is the largest model the MacBook Pro 14-inch (M5) can run?

Qwen3.6 35B A3B (36.0B) is the largest at 4-bit or better: at Q4_K_M it uses 22.0 GB, 77% of the available memory, and runs at about 28.6 tok/s.

Can the MacBook Pro 14-inch (M5) run 70B models?

No. Llama 3.3 70B Instruct needs 51.3 GB at Q4, more than the 28.5 GB available.

How long does the MacBook Pro 14-inch (M5) take to read a long prompt?

On Qwen3.6 35B A3B, about 12 s for a 4K-token prompt and 1.6 min for a 32K-token document before the first word appears.

Is renting a GPU cheaper than buying the MacBook Pro 14-inch (M5)?

An A100 (40 GB) rents from $0.40/hr. Renting costs as much as buying after ≈4,600 hours (≈3.1 years at 4 h a day).

24 GB GPUs All Macs Laptops Mac Studio M1 Max Mac Studio M2 Max MacBook Pro 14" M1 Max MacBook Pro 14" M2 Max MacBook Pro 16" M1 Max MacBook Pro 16" M2 Max MacBook Pro 16" M4 Max Best coding LLMs All hardware