Apple · M4 Pro · Laptop

Best AI Models for MacBook Pro 16" M4 Pro (24 GB)

Runs 14B models well and fits 35B MoE; dense 27–31B fits but is slow at 11 tok/s, and 70B doesn't fit in 20.5 GB.

24 GB unified20.5 GB for models273 GB/s17 TFLOPS FP162024

Buy$2,499

Memory

24 GB$2,499 48 GB

Same chip in

MacBook Pro 16"$2,499 Mac Mini$1,599 MacBook Pro 14"$1,999

What LLMs can the MacBook Pro 16" M4 Pro run?

#	Model	Speed	Quant · Memory
1	Qwen3.8 27BAlibabaHow to run → Q4_K_M · 17.9 GB · 11.0 t/s	11.0 tok/s	Q4_K_M · 17.9 GB
2	Qwen3.6 27BAlibaba Q4_K_M · 17.9 GB · 11.0 t/s	11.0 tok/s	Q4_K_M · 17.9 GB
3	Gemma 4 26B A4B ITGoogle Q4_K_M · 16.5 GB · 49.1 t/s	49.1 tok/s	Q4_K_M · 16.5 GB
4	GPT OSS 20BOpenAI Q4_K_M · 13.1 GB · 54.5 t/s	54.5 tok/s	Q4_K_M · 13.1 GB
5	LFM2.5 24B A2BLiquid AI Q4_K_M · 15.0 GB · 62.7 t/s	62.7 tok/s	Q4_K_M · 15.0 GB

#	Model	Speed	Quant · Memory
1	Gemma 4 26B A4B ITGoogleHow to run → Q4_K_M · 16.5 GB · 49.1 t/s	49.1 tok/s	Q4_K_M · 16.5 GB
2	GPT OSS 20BOpenAI Q4_K_M · 13.1 GB · 54.5 t/s	54.5 tok/s	Q4_K_M · 13.1 GB
3	Llama 3.1 8B InstructMeta Q4_K_M · 7.9 GB · 36.1 t/s	36.1 tok/s	Q4_K_M · 7.9 GB
4	Qwen3.8 27BAlibaba Q4_K_M · 17.9 GB · 11.0 t/s	11.0 tok/s	Q4_K_M · 17.9 GB
5	LFM2.5 24B A2BLiquid AI Q4_K_M · 15.0 GB · 62.7 t/s	62.7 tok/s	Q4_K_M · 15.0 GB

#	Model	Speed	Quant · Memory
1	Gemma 4 26B A4B ITGoogleHow to run → Q4_K_M · 16.5 GB · 49.1 t/s	49.1 tok/s	Q4_K_M · 16.5 GB
2	Qwen3.5 9BAlibaba Q4_K_M · 6.6 GB · 30.0 t/s	30.0 tok/s	Q4_K_M · 6.6 GB
3	GPT OSS 20BOpenAI Q4_K_M · 13.1 GB · 54.5 t/s	54.5 tok/s	Q4_K_M · 13.1 GB
4	Qwen3 8BAlibaba Q4_K_M · 7.6 GB · 34.6 t/s	34.6 tok/s	Q4_K_M · 7.6 GB
5	LFM2.5 24B A2BLiquid AI Q4_K_M · 15.0 GB · 62.7 t/s	62.7 tok/s	Q4_K_M · 15.0 GB

#	Model	Speed	Quant · Memory
1	Qwen3.5 9BAlibabaHow to run → Q4_K_M · 6.6 GB · 30.0 t/s	30.0 tok/s	Q4_K_M · 6.6 GB
2	Qwen3.5 4BAlibaba Q4_K_M · 3.4 GB · 58.6 t/s	58.6 tok/s	Q4_K_M · 3.4 GB
3	GPT OSS 20BOpenAI Q4_K_M · 13.1 GB · 54.5 t/s	54.5 tok/s	Q4_K_M · 13.1 GB
4	Mistral Nemo Instruct 2407Mistral AI Q4_K_M · 11.0 GB · 23.7 t/s	23.7 tok/s	Q4_K_M · 11.0 GB
5	LFM2.5 24B A2BLiquid AI Q4_K_M · 15.0 GB · 62.7 t/s	62.7 tok/s	Q4_K_M · 15.0 GB

#	Model	Speed ↓	Quant · Memory
1	Qwen3.5 4BAlibabaHow to run → Q4_K_M · 3.4 GB · 58.6 t/s	58.6 tok/s	Q4_K_M · 3.4 GB
2	LFM2.5 24B A2BLiquid AI Q4_K_M · 15.0 GB · 62.7 t/s	62.7 tok/s	Q4_K_M · 15.0 GB
3	GPT OSS 20BOpenAI Q4_K_M · 13.1 GB · 54.5 t/s	54.5 tok/s	Q4_K_M · 13.1 GB
4	Gemma 4 26B A4B ITGoogle Q4_K_M · 16.5 GB · 49.1 t/s	49.1 tok/s	Q4_K_M · 16.5 GB
5	Qwen3.5 9BAlibaba Q4_K_M · 6.6 GB · 30.0 t/s	30.0 tok/s	Q4_K_M · 6.6 GB

#	Model	Speed	Quant · Memory
1	Gemma 4 26B A4B ITGoogleHow to run → Q4_K_M · 16.5 GB · 49.1 t/s	49.1 tok/s	Q4_K_M · 16.5 GB
2	Qwen3.5 9BAlibaba Q4_K_M · 6.6 GB · 30.0 t/s	30.0 tok/s	Q4_K_M · 6.6 GB
3	Qwen3.5 4BAlibaba Q4_K_M · 3.4 GB · 58.6 t/s	58.6 tok/s	Q4_K_M · 3.4 GB
4	Gemma 3 12B ITGoogle Q4_K_M · 10.9 GB · 23.8 t/s	23.8 tok/s	Q4_K_M · 10.9 GB
5	MiMo V2.6 Distill Qwen 9BXiaomi Q4_K_M · 6.5 GB · 30.8 t/s	30.8 tok/s	Q4_K_M · 6.5 GB

See all 320 models on the MacBook Pro 16" M4 Pro →Bars = traction for models without a Score yet

About the MacBook Pro 16" M4 Pro (24 GB)

The MacBook Pro 16" M4 Pro is one of the fastest 24 GB machines: it runs 14B models well and fits 35B MoE. Among 24 GB machines, only the M5 Pro write faster. macOS keeps about 3.5 GB, leaving 20.5 GB for models. With 17 TFLOPS it reads long prompts faster than most 24 GB machines: a 4K-token prompt takes 66 s. At its $2,499 MSRP it gives 12.0 tok/s per $1,000, 6th of the 7 machines compared here. M4 Pro generation, released 2024; the newer M5 Pro writes 13% faster with 1.9× the compute.

Speed in 24 GB#2273 GB/s

Prompt reading#217 TFLOPS

For models20.5 GBmacOS keeps 3.5 GB

ChipM4 Proreleased 2024

MacBook Pro 16" M4 Pro strengths and weaknesses

Strengths

Runs 35B MoE models: Qwen3.6 35B A3B at 46.3 tok/s in 19.8 GB

Weaknesses

70B models don't fit: Llama 3.3 70B Instruct needs 51.3 GB at Q4 vs 20.5 GB usable here
Slow on large dense models: Qwen3.8 27B at 11.0 tok/s
Slow prompt reading: A 32K-token prompt on Qwen3.8 27B waits 8.8 min for the first token
No CUDA: vLLM, AWQ, GPTQ and FP8 builds don't run; use GGUF or MLX

Memory for models

20.5 GB of 24 GB

9B6.6 GB14B11.9 GB27–31B17.9 GB35B MoE19.8 GB

9B6.6 GB14B11.9 GB35B MoE19.8 GB

For models 20.5 GBmacOS keeps 3.5 GBModel size at Q4

70B models need 51.3 GB at Q4, more than the 20.5 GB available. The 48 GB config fits Qwen3.8 27B →Or rent an H100 (80 GB) from $2.69/hr →

Speed per dollar and per watt

NewUsed

On Qwen3.5 9B (9B params) 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. The MacBook Pro 16" M4 Pro has no current new price, so it is shown at its MSRP.

Machine	New price	tok/s	tok/s per $1,000	tok/s per 100 W
RTX 509032 GB	about $5,376	183	34.1	31.8
Mac Mini M4 Pro24 GB	about $1,599	30.0	18.8	21.4
Mac Studio M4 Max36 GB	about $2,499	45.1	18.0	31.1
MacBook Pro 14" M4 Pro24 GB	about $1,999	30.0	15.0	–
MacBook Pro 14 M5 Pro64 GB	about $2,299	33.8	14.7	–
MacBook Pro 16" M4 Pro24 GB	about $2,499	30.0	12.0	–
MacBook Air 13" M424 GB	about $1,399	13.2	9.4	–

Machine	Used price	tok/s	tok/s per $1,000	tok/s per 100 W
RTX 409024 GBBest used value	about $3,000	103	34.3	22.9
RTX 509032 GB	about $6,400	183	28.6	31.8
Mac Studio M4 Max36 GB	about $2,000	45.1	22.6	31.1
MacBook Pro 14 M5 Pro64 GB	about $2,109	33.8	16.0	–

Cost per token: the MacBook Pro 16" M4 Pro against 24–64 GB machines and GPUs

On Qwen3.5 9B (9B params, 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 Qwen3.5 9B · card over 3 years + power

$5.28

Machine, MSRP: $5.28
Power: not published

3-year cost of ownership$2,499

Or rent an RTX 5090 in the cloud$0.46/hr

Renting costs as much as buying after ≈5,400 hours (≈3.7 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 Qwen3.5 9B.

Same chip, 2× the memoryMacBook Pro 16" M4 Pro (48 GB)Apple · 44.5 GB for models · M4 Pro

same speed▲ 24 GBno price

Same family Laptop, 56% slowerMacBook Air 13" M4 (24 GB)Apple · 20.5 GB for models · M4

▼ 56% speedsame memory$1,399

50% faster, 12 GB more memoryMac Studio M4 Max (36 GB)Apple · 32.5 GB for models · M4 Max

▲ 50% speed▲ 12 GB$2,499

13% faster, 40 GB more memoryMacBook Pro 14 M5 ProApple · 60.5 GB for models · M5 Pro

▲ 13% speed▲ 40 GB$2,299

Reads prompts 22× faster, 24 GB for modelsRTX 4090NVIDIA · 24 GB VRAM · GPU

▲ 22× prompts▲ 243% speed▲ 3.5 GB$1,599rent $0.34/hr

Reads prompts 27× faster, 32 GB for modelsRTX 5090NVIDIA · 32 GB VRAM · GPU

▲ 27× prompts▲ 510% speed▲ 11.5 GB$5,376rent $0.50/hr

MacBook Pro 16" M4 Pro tokens per second by model size

Output speed depends on memory bandwidth (273 GB/s). Grey rows need more than the 20.5 GB available.

9BQwen3.5 9B · Q4_K_M · 6.6 GB
30.0tok/s
14BQwen3 14B · Q4_K_M · 11.9 GB
20.1tok/s
27–31BQwen3.8 27B · Q4_K_M · 17.9 GB
11.0tok/s
35B MoEQwen3.6 35B A3B · IQ4_XS · 19.8 GB tight · IQ4_XS
46.3tok/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

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 3.1×. Indexed to the M1 Pro; speeds on Qwen3.5 9B, same 16 GB.

All 1125 models on the MacBook Pro 16" M4 Pro

Featured only

Best quant that fits in 20.5 GB, ordered by llmrun Score. Fit grades how well it runs here, S best. How ranking works

LLM models compatible with MacBook Pro 16" M4 Pro (24 GB) — ranked by Score, recency and Fit
Model	Quant	VRAM	Speed	Context	Fit
VibeThinker 1.5B1.8BChatMathCode Q4_K_M·134.6 t/s	Q4_K_M	1.8 GB9%	134.6 t/s	131K	S95, Runs great
XCurOS0.1 8B Instruct7.6BChatFunctions BF16·12.2 t/s	BF16	16.5 GB80%	12.2 t/s	33K	B51, Decent
Granite 4.0 1B1.6BChatFunctions Q4_K_M·131.8 t/s	Q4_K_M	2.6 GB13%	131.8 t/s	131K	S95, Runs great
Gemma 3 270M IT Heretic268MChat Q4_K_M·398.1 t/s	Q4_K_M	0.5 GB2%	398.1 t/s	33K	S100, Runs great
Ouro 2.6B Thinking2.7BChatReasoning BF16·29.7 t/s	BF16	12.1 GB59%	29.7 t/s	66K	A71, Runs well
SmolVLM Instruct2.2BVision Q4_K_M·93.2 t/s	Q4_K_M	4.9 GB24%	93.2 t/s	16K	S90, Runs great
Sarvam 30B32.2BChatFunctions Q4_K_M·54.8 t/s	Q4_K_M	19.9 GB97%	54.8 t/s	131K	B56, Decent
OLMo 2 0425 1B Instruct1.5BChat Q4_K_M·130.9 t/s	Q4_K_M	1.7 GB8%	130.9 t/s	4K	S95, Runs great
Supergemma4 E4b Abliterated7.5BChat Q4_K_M·38.0 t/s	Q4_K_M	5.3 GB26%	38.0 t/s	131K	A74, Runs well
Qwen3.5 9B Uncensored9BChat Q4_K_M·32.2 t/s	Q4_K_M	8.6 GB42%	32.2 t/s	—	A71, Runs well
Qwen3 4B Instruct 2507 Heretic4.0BChat Q4_K_M·65.9 t/s	Q4_K_M	4.2 GB21%	65.9 t/s	262K	S85, Runs great
Hermes 3 Llama 3.1 8B8.0BChatRoleplayFunctions Q4_K_M·35.5 t/s	Q4_K_M	7.3 GB35%	35.5 t/s	131K	A73, Runs well
Falcon H1 7B Instruct7.6BChatFunctions Q4_K_M·37.9 t/s	Q4_K_M	6.3 GB31%	37.9 t/s	262K	A74, Runs well
JOSIE 1.1 4B Instruct4.0BChat Q4_K_M·65.9 t/s	Q4_K_M	4.2 GB21%	65.9 t/s	262K	S85, Runs great
Sweep Next Edit v2 7B7.6BChatCode Q4_K_M·38.3 t/s	Q4_K_M	5.8 GB28%	38.3 t/s	33K	A75, Runs well

MacBook Pro 16" M4 Pro specs

Specs

Chip: M4 Pro
CPU cores: 14
GPU cores: 20
Unified memory: 24 GB
For models: 20.5 GB (macOS keeps 3.5 GB)
Memory bandwidth: 273 GB/s
FP16 (dense): 17.2 TFLOPS
Neural Engine: 38 TOPS
Released: 2024-11-08
MSRP: $2,499

MacBook Pro 16" M4 Pro FAQ

Is the MacBook Pro 16" M4 Pro (24 GB) worth it for local LLMs in 2026?

At its $2,499 MSRP it gives 12.0 tok/s per $1,000 on Qwen3.5 9B, 6th of the 7 machines compared here. It runs 14B models well and fits 35B MoE; dense 27–31B fits but is slow at 11 tok/s, and 70B doesn't fit in 20.5 GB.

How much memory is available for AI on the MacBook Pro 16" M4 Pro (24 GB)?

About 20.5 GB of the 24 GB. macOS keeps roughly 3.5 GB for itself and other apps.

What is the largest model the MacBook Pro 16" M4 Pro (24 GB) can run?

Qwen3.6 35B A3B (36.0B) is the largest at 4-bit or better: at IQ4_XS it uses 19.8 GB, 97% of the available memory, and runs at about 46.3 tok/s.

Can the MacBook Pro 16" M4 Pro (24 GB) run Qwen3.8 27B?

Yes. Qwen3.8 27B fits at Q4_K_M, using 17.9 GB of the 20.5 GB available, and it is the best model that runs well on this machine.

Can the MacBook Pro 16" M4 Pro (24 GB) run 70B models?

No. Llama 3.3 70B Instruct needs 51.3 GB at Q4, more than the 20.5 GB available.

How long does the MacBook Pro 16" M4 Pro (24 GB) take to read a long prompt?

On Qwen3.8 27B, about 66 s for a 4K-token prompt and 8.8 min for a 32K-token document before the first word appears.

Is renting a GPU cheaper than buying the MacBook Pro 16" M4 Pro?

An RTX 5090 (32 GB) rents from $0.46/hr. Renting costs as much as buying after ≈5,400 hours (≈3.7 years at 4 h a day).

16 GB GPUs All Macs Laptops Mac Mini M5 Pro MacBook Pro 14" M5 Pro MacBook Pro 16" M5 Pro MacBook Air 13" M5 Mac Mini M4 Best coding LLMs All hardware