← All MacBook Pro 16" models

MacBook Pro 16" M3 Pro

The M3 Pro MacBook Pro 16" runs local models at 150 GB/s of memory bandwidth with 18 to 36 GB of unified memory. On Apple Silicon that memory is shared with the GPU, so the whole pool is available for weights: at 36 GB you can hold roughly a 47B dense model at Q4. The Pro roughly doubles the base chip's memory bus. That moves mid-size models from usable to comfortable without moving you into desktop money.

Apple no longer sells this configuration new. It stays fully evaluated here because the used market is where most of its local AI value now sits.

By , Founder & Lead Engineer— Updated

Specifications

ChipApple M3 Pro
CPU cores12
GPU cores18
Unified memory18 or 36 GB
Memory bandwidth150 GB/s
Neural Engine18 TOPS
Released2023
AvailabilityUsed market

Memory bandwidth is faster than 20% of the Apple Silicon chips shipped in a Mac, against a 1228 GB/s peak.

Its memory ceiling is above 40% of them, against a 512 GB peak.

Pick your configuration

Every option Apple sells with this chip. The model list below recomputes against the one you pick.

Unified memory

What each memory option runs

Unified memory is the ceiling and it is soldered, so this is the decision you cannot revisit.

18 GB unified memory

15 GB usable for weights · 150 GB/s

5,843 of 6,563 models fit, and 5,265 of them run with headroom rather than as a squeeze.

Largest model at Q4
Laguna M.1 JANG_1L · 22.86B
Best all-round pick
MiniCPM5 1B · Q8_0 · ~73 tok/s

36 GB unified memory

31 GB usable for weights · 150 GB/s

6,120 of 6,563 models fit, and 5,827 of them run with headroom rather than as a squeeze.

Largest model at Q4
Chinese Mixtral 8x7B · 46.91B
Best all-round pick
MiniCPM5 1B · Q8_0 · ~73 tok/s

What a 18 GB M3 Pro MacBook Pro 16" can run

Every model in the database against this exact configuration, at 150 GB/s. Ratings and speeds are the same numbers the model pages show.

Showing 6563 of 6563 models

General · openbmb · 2026-05-21

Q8_0Excellent
1.7 GB9% of RAM~73 tok/sEstimated1.08B params
Run with ToolPiper

General · Liquid AI · 2026-06-24

Q8_0Excellent
0.8 GB4% of RAM~342 tok/sEstimated0.23B params
Run with ToolPiper

General · ktruestory · 2026-05-28

Q8_0Excellent
1.7 GB9% of RAM~73 tok/sEstimated1.08B params
Run with ToolPiper

General · petrouil · 2026-07-23

Q8_0Excellent
3.4 GB19% of RAMBenchmark needed2.61B params
Run with ToolPiper

Multimodal · Alibaba · 2026-02-28

Q8_0Excellent
1.5 GB8% of RAM~90 tok/sEstimated0.87B params
Run with ToolPiper

General · radixark · 2026-07-27

Q8_0Excellent
3.0 GB17% of RAM~35 tok/sEstimated2.25B params
Run with ToolPiper

Multimodal · Alibaba · 2026-02-28

Q8_0Excellent
1.5 GB8% of RAM~90 tok/sEstimated0.87B params
Run with ToolPiper

General · Liquid AI · 2026-05-28

Q8_0Excellent
9.9 GB55% of RAMBenchmark needed8.47B params
Run with ToolPiper

General · Liquid AI · 2026-03-31

Q8_0Excellent
0.9 GB5% of RAM~224 tok/sEstimated0.35B params
Run with ToolPiper

General · goekdeniz-guelmez · 2026-07-31

Q8_0Excellent
3.0 GB17% of RAM~35 tok/sEstimated2.27B params
Run with ToolPiper

General · cagrigungor · 2026-08-06

Q8_0Excellent
0.8 GB4% of RAM~291 tok/sEstimated0.27B params
Run with ToolPiper

Multimodal · Alibaba · 2026-02-28

Q8_0Excellent
3.0 GB17% of RAM~35 tok/sEstimated2.27B params
Run with ToolPiper

General · farbodtavakkoli · 2026-06-17

Q8_0Excellent
10.8 GB60% of RAMBenchmark needed9.23B params
Run with ToolPiper

Multimodal · Alibaba · 2026-02-28

Q8_0Excellent
3.0 GB17% of RAM~35 tok/sEstimated2.27B params
Run with ToolPiper

General · Liquid AI · 2026-07-28

Q8_0Excellent
3.5 GB20% of RAM~29 tok/sEstimated2.7B params
Run with ToolPiper

General · Liquid AI · 2026-01-20

Q8_0Excellent
1.8 GB10% of RAM~67 tok/sEstimated1.17B params
Run with ToolPiper

Reasoning · openonerec · 2026-06-09

Q8_0Excellent
1.4 GB8% of RAM~98 tok/sEstimated0.8B params
Run with ToolPiper

General · Liquid AI · 2026-01-05

Q8_0Excellent
1.8 GB10% of RAM~67 tok/sEstimated1.17B params
Run with ToolPiper

General · Liquid AI · 2026-01-04

Q8_0Excellent
1.8 GB10% of RAM~67 tok/sEstimated1.17B params
Run with ToolPiper

Multimodal · Liquid AI · 2026-01-05

Q8_0Excellent
2.3 GB13% of RAM~49 tok/sEstimated1.6B params
Run with ToolPiper

General · Liquid AI · 2025-10-28

Q8_0Excellent
0.9 GB5% of RAM~224 tok/sEstimated0.35B params
Run with ToolPiper

General · frontiersmind · 2026-08-03

Q8_0Excellent
1.2 GB7% of RAM~121 tok/sEstimated0.65B params
Run with ToolPiper

Chat · Liquid AI · 2026-01-06

Q8_0Excellent
1.8 GB10% of RAM~67 tok/sEstimated1.17B params
Run with ToolPiper

General · ibm-granite · 2025-09-16

Q8_0Excellent
8.2 GB46% of RAMBenchmark needed6.94B params
Run with ToolPiper

Multimodal · Liquid AI · 2025-08-12

Q8_0Excellent
1.0 GB6% of RAM~175 tok/sEstimated0.45B params
Run with ToolPiper

General · Liquid AI · 2025-09-30

Q8_0Excellent
0.9 GB5% of RAM~224 tok/sEstimated0.35B params
Run with ToolPiper

General · Liquid AI · 2025-08-22

Q8_0Excellent
1.8 GB10% of RAM~67 tok/sEstimated1.17B params
Run with ToolPiper

General · Liquid AI · 2025-09-03

Q8_0Excellent
0.9 GB5% of RAM~224 tok/sEstimated0.35B params
Run with ToolPiper

General · Liquid AI · 2025-09-03

Q8_0Excellent
1.8 GB10% of RAM~67 tok/sEstimated1.17B params
Run with ToolPiper

General · Liquid AI · 2025-08-25

Q8_0Excellent
0.9 GB5% of RAM~224 tok/sEstimated0.35B params
Run with ToolPiper

General · Liquid AI · 2025-09-03

Q8_0Excellent
0.9 GB5% of RAM~224 tok/sEstimated0.35B params
Run with ToolPiper

General · Liquid AI · 2025-09-03

Q8_0Excellent
1.8 GB10% of RAM~67 tok/sEstimated1.17B params
Run with ToolPiper

General · NCAI · 2025-12-29

Q8_0Excellent
8.6 GB48% of RAMBenchmark needed7.25B params
Run with ToolPiper

General · hmellor · 2025-07-22

Q8_0Excellent
1.9 GB10% of RAM~63 tok/sEstimated1.24B params
Run with ToolPiper

General · weiboai · 2026-06-12

Q8_0Excellent
3.9 GB22% of RAM~25 tok/sEstimated3.09B params
Run with ToolPiper

General · ibm-granite · 2025-04-30

Q8_0Excellent
7.9 GB44% of RAMBenchmark needed6.67B params
Run with ToolPiper

General · Liquid AI · 2025-07-10

Q8_0Excellent
1.8 GB10% of RAM~67 tok/sEstimated1.17B params
Run with ToolPiper

General · stefanruseti · 2025-06-04

Q8_0Excellent
1.9 GB10% of RAM~63 tok/sEstimated1.24B params
Run with ToolPiper

General · ma7ee7 · 2026-07-30

Q8_0Excellent
4.0 GB22% of RAM~25 tok/sEstimated3.13B params
Run with ToolPiper

General · bytedance · 2025-10-28

Q8_0Excellent
2.1 GB12% of RAM~55 tok/sEstimated1.43B params
Run with ToolPiper

General · Liquid AI · 2025-10-07

Q8_0Excellent
9.8 GB54% of RAMBenchmark needed8.34B params
Run with ToolPiper

Multimodal · Liquid AI · 2025-08-12

Q8_0Excellent
2.3 GB13% of RAM~50 tok/sEstimated1.58B params
Run with ToolPiper

General · lgai-exaone · 2025-07-11

Q8_0Excellent
1.9 GB11% of RAM~61 tok/sEstimated1.28B params
Run with ToolPiper

General · Liquid AI · 2025-07-10

Q8_0Excellent
0.9 GB5% of RAM~224 tok/sEstimated0.35B params
Run with ToolPiper

General · Liquid AI · 2025-07-10

Q8_0Excellent
1.3 GB7% of RAM~106 tok/sEstimated0.74B params
Run with ToolPiper

General · Liquid AI · 2025-12-25

Q8_0Excellent
3.4 GB19% of RAM~31 tok/sEstimated2.57B params
Run with ToolPiper

General · Liquid AI · 2026-01-05

Q8_0Excellent
3.4 GB19% of RAM~31 tok/sEstimated2.57B params
Run with ToolPiper

Multimodal · NCAI · 2025-12-29

Q8_0Excellent
9.0 GB50% of RAMBenchmark needed7.58B params
Run with ToolPiper

Multimodal · ibm-granite · 2026-04-16

Q8_0Excellent
5.0 GB28% of RAM~20 tok/sEstimated4B params
Run with ToolPiper

General · Alibaba · 2025-09-23

Q8_0Excellent
1.3 GB7% of RAM~105 tok/sEstimated0.75B params
Run with ToolPiper

General · openonerec · 2025-12-30

Q8_0Excellent
2.9 GB16% of RAM~37 tok/sEstimated2.13B params
Run with ToolPiper

General · amd · 2025-05-17

Q8_0Excellent
2.2 GB12% of RAM~52 tok/sEstimated1.5B params
Run with ToolPiper

General · pfnet · 2025-02-05

Q8_0Excellent
1.9 GB11% of RAM~61 tok/sEstimated1.29B params
Run with ToolPiper

General · sapientinc · 2026-05-17

Q8_0Excellent
1.8 GB10% of RAM~67 tok/sEstimated1.18B params
Run with ToolPiper

General · ibm-granite · 2025-10-07

Q8_0Excellent
0.9 GB5% of RAM~224 tok/sEstimated0.35B params
Run with ToolPiper

General · Liquid AI · 2025-09-22

Q8_0Excellent
3.4 GB19% of RAM~31 tok/sEstimated2.57B params
Run with ToolPiper

General · viorikaai-org · 2026-07-05

Q8_0Excellent
0.6 GB3% of RAM~1,571 tok/sEstimated0.05B params
Run with ToolPiper

General · bananamind · 2026-07-17

Q8_0Excellent
0.5 GB3% of RAM~7,857 tok/sEstimated0.01B params
Run with ToolPiper

General · maliosdark · 2026-07-09

Q8_0Excellent
0.6 GB3% of RAM~1,571 tok/sEstimated0.05B params
Run with ToolPiper

General · raidium · 2026-06-15

Q8_0Excellent
0.5 GB3% of RAM~3,929 tok/sEstimated0.02B params
Run with ToolPiper

Embedding · taide · 2026-06-12

Q8_0Excellent
0.8 GB5% of RAM~262 tok/sEstimated0.3B params
Run with ToolPiper

General · Alibaba · 2025-04-27

Q8_0Excellent
1.3 GB7% of RAM~105 tok/sEstimated0.75B params
Run with ToolPiper

Multimodal · zai-org

Q8_0Excellent
2.0 GB11% of RAM~59 tok/sEstimated1.33B params
Run with ToolPiper

Multimodal · datalab-to

Q8_0Excellent
1.3 GB7% of RAM~114 tok/sEstimated0.69B params
Run with ToolPiper

Multimodal · openbmb

Q8_0Excellent
2.0 GB11% of RAM~60 tok/sEstimated1.3B params
Run with ToolPiper

General · Alibaba · 2025-04-28

Q8_0Excellent
1.2 GB6% of RAM~131 tok/sEstimated0.6B params
Run with ToolPiper

Reasoning · DeepSeek · 2025-01-20

Q8_0Excellent
2.5 GB14% of RAM~44 tok/sEstimated1.78B params
Run with ToolPiper

Multimodal · tencent

Q8_0Excellent
1.7 GB10% of RAMBenchmark needed1.12B params
Run with ToolPiper

General · distil-labs

Q8_0Excellent
0.9 GB5% of RAM~224 tok/sEstimated0.35B params
Run with ToolPiper

General · farbodtavakkoli

Q8_0Excellent
1.8 GB10% of RAM~65 tok/sEstimated1.21B params
Run with ToolPiper

Multimodal · ath-maas

Q8_0Excellent
1.4 GB8% of RAM~92 tok/sEstimated0.85B params
Run with ToolPiper

Multimodal · Liquid AI

Q8_0Excellent
1.0 GB6% of RAM~175 tok/sEstimated0.45B params
Run with ToolPiper

Multimodal · paddlepaddle

Q8_0Excellent
1.6 GB9% of RAM~82 tok/sEstimated0.96B params
Run with ToolPiper

General · Liquid AI

Q8_0Excellent
0.9 GB5% of RAM~224 tok/sEstimated0.35B params
Run with ToolPiper

Chat · uzlm · 2025-09-03

Q8_0Excellent
1.9 GB10% of RAM~63 tok/sEstimated1.24B params
Run with ToolPiper

Multimodal · paddlepaddle

Q8_0Excellent
1.6 GB9% of RAM~82 tok/sEstimated0.96B params
Run with ToolPiper

General · adamlucek

Q8_0Excellent
1.9 GB10% of RAM~63 tok/sEstimated1.24B params
Run with ToolPiper

Coding · shahriarferdoush

Q8_0Excellent
1.9 GB10% of RAM~63 tok/sEstimated1.24B params
Run with ToolPiper

General · ahczhg

Q8_0Excellent
1.9 GB10% of RAM~63 tok/sEstimated1.24B params
Run with ToolPiper

General · onnx-community · 2025-04-28

Q8_0Excellent
1.0 GB6% of RAM~175 tok/sEstimated0.45B params
Run with ToolPiper

General · etherll

Q8_0Excellent
1.3 GB7% of RAM~106 tok/sEstimated0.74B params
Run with ToolPiper

General · baidu

Q8_0Excellent
0.9 GB5% of RAM~218 tok/sEstimated0.36B params
Run with ToolPiper

General · Liquid AI

Q8_0Excellent
1.8 GB10% of RAM~67 tok/sEstimated1.17B params
Run with ToolPiper

General · openbmb

Q8_0Excellent
1.7 GB9% of RAM~73 tok/sEstimated1.08B params
Run with ToolPiper

General · benjamin

Q8_0Excellent
1.7 GB9% of RAM~73 tok/sEstimated1.07B params
Run with ToolPiper

General · lemonelabs

Q8_0Excellent
1.8 GB10% of RAM~65 tok/sEstimated1.21B params
Run with ToolPiper

General · openbmb · 2025-06-05

Q8_0Excellent
1.0 GB5% of RAM~183 tok/sEstimated0.43B params
Run with ToolPiper

General · farbodtavakkoli

Q8_0Excellent
2.5 GB14% of RAMBenchmark needed1.77B params
Run with ToolPiper

General · novachronoai

Q8_0Excellent
1.8 GB10% of RAM~65 tok/sEstimated1.21B params
Run with ToolPiper

Multimodal · paddlepaddle

Q8_0Excellent
1.6 GB9% of RAM~82 tok/sEstimated0.96B params
Run with ToolPiper

General · kamilamila

Q8_0Excellent
1.2 GB7% of RAM~127 tok/sEstimated0.62B params
Run with ToolPiper

General · arcee-ai

Q8_0Excellent
7.3 GB41% of RAMBenchmark needed6.12B params
Run with ToolPiper

Multimodal · Liquid AI · 2025-10-22

Q8_0Excellent
3.8 GB21% of RAM~26 tok/sEstimated3B params
Run with ToolPiper

General · Liquid AI

Q8_0Excellent
1.8 GB10% of RAM~65 tok/sEstimated1.21B params
Run with ToolPiper
Q8_0Excellent
1.7 GB9% of RAM~73 tok/sEstimated1.08B params
Run with ToolPiper

General · ordenwills

Q8_0Excellent
0.9 GB5% of RAM~224 tok/sEstimated0.35B params
Run with ToolPiper
Q8_0Excellent
2.1 GB11% of RAM~57 tok/sEstimated1.39B params
Run with ToolPiper

General · carsenk

Q8_0Excellent
1.9 GB10% of RAM~63 tok/sEstimated1.24B params
Run with ToolPiper

Reasoning · nvidia

Q8_0Excellent
2.2 GB12% of RAM~51 tok/sEstimated1.54B params
Run with ToolPiper

General · openbmb

Q8_0Excellent
2.0 GB11% of RAM~60 tok/sEstimated1.3B params
Run with ToolPiper

General · pyoakum

Q8_0Excellent
6.5 GB36% of RAMBenchmark needed5.35B params
Run with ToolPiper

General · ibm-granite

Q8_0Excellent
4.2 GB23% of RAMBenchmark needed3.3B params
Run with ToolPiper
Q8_0Excellent
2.0 GB11% of RAM~60 tok/sEstimated1.3B params
Run with ToolPiper

General · skis-ai-research

Q8_0Excellent
1.8 GB10% of RAM~67 tok/sEstimated1.17B params
Run with ToolPiper

General · thkim0305

Q8_0Excellent
1.6 GB9% of RAM~79 tok/sEstimated1B params
Run with ToolPiper
Q8_0Excellent
1.5 GB8% of RAM~90 tok/sEstimated0.87B params
Run with ToolPiper

Coding · rahul7star

Q8_0Excellent
1.5 GB8% of RAM~90 tok/sEstimated0.87B params
Run with ToolPiper

General · fableforge-ai · 2026-07-05

Q8_0Excellent
2.2 GB12% of RAM~51 tok/sEstimated1.54B params
Run with ToolPiper
Q8_0Excellent
6.9 GB38% of RAMBenchmark needed5.75B params
Run with ToolPiper

General · artificialguybr

Q8_0Excellent
1.9 GB10% of RAM~63 tok/sEstimated1.24B params
Run with ToolPiper

General · Microsoft

Q8_0Excellent
0.7 GB4% of RAMBenchmark needed0.17B params
Run with ToolPiper

General · Microsoft

Q8_0Excellent
0.7 GB4% of RAMBenchmark needed0.17B params
Run with ToolPiper

General · tencent

Q8_0Excellent
1.1 GB6% of RAM~146 tok/sEstimated0.54B params
Run with ToolPiper

General · primeintellect

Q8_0Excellent
1.1 GB6% of RAMBenchmark needed0.54B params
Run with ToolPiper

General · reaperdoesntknow

Q8_0Excellent
1.6 GB9% of RAM~78 tok/sEstimated1.01B params
Run with ToolPiper

General · darthcrawl · 2026-05-07

Q8_0Excellent
0.5 GB3% of RAM~1,964 tok/sEstimated0.04B params
Run with ToolPiper

General · appvoid

Q8_0Excellent
0.6 GB3% of RAM~873 tok/sEstimated0.09B params
Run with ToolPiper

General · pinkstack

Q8_0Excellent
0.9 GB5% of RAM~224 tok/sEstimated0.35B params
Run with ToolPiper

Coding · Liquid AI

Q8_0Excellent
0.9 GB5% of RAM~224 tok/sEstimated0.35B params
Run with ToolPiper

General · squ11z1

Q8_0Excellent
0.9 GB5% of RAM~224 tok/sEstimated0.35B params
Run with ToolPiper

General · iselabvn

Q8_0Excellent
0.9 GB5% of RAM~224 tok/sEstimated0.35B params
Run with ToolPiper

General · meddies

Q8_0Excellent
0.9 GB5% of RAM~224 tok/sEstimated0.35B params
Run with ToolPiper

General · mihaipopa-1

Q8_0Excellent
0.9 GB5% of RAM~224 tok/sEstimated0.35B params
Run with ToolPiper

General · lazos

Q8_0Excellent
0.9 GB5% of RAM~224 tok/sEstimated0.35B params
Run with ToolPiper

General · q1ngmang

Q8_0Excellent
0.9 GB5% of RAM~224 tok/sEstimated0.35B params
Run with ToolPiper

General · baidu

Q8_0Excellent
0.9 GB5% of RAM~218 tok/sEstimated0.36B params
Run with ToolPiper

Multimodal · Liquid AI

Q8_0Excellent
1.0 GB6% of RAM~175 tok/sEstimated0.45B params
Run with ToolPiper
Q8_0Excellent
1.2 GB7% of RAM~127 tok/sEstimated0.62B params
Run with ToolPiper

General · melikegks

Q8_0Excellent
1.3 GB7% of RAM~105 tok/sEstimated0.75B params
Run with ToolPiper
Q8_0Excellent
1.3 GB7% of RAM~105 tok/sEstimated0.75B params
Run with ToolPiper

Reasoning · supralabs

Q8_0Excellent
1.3 GB7% of RAM~105 tok/sEstimated0.75B params
Run with ToolPiper

General · iselabvn

Q8_0Excellent
1.3 GB7% of RAM~105 tok/sEstimated0.75B params
Run with ToolPiper

Multimodal · 8f-ai

Q8_0Excellent
1.3 GB7% of RAM~105 tok/sEstimated0.75B params
Run with ToolPiper

General · kylesayrs

Q8_0Excellent
1.4 GB8% of RAMBenchmark needed0.8B params
Run with ToolPiper

General · inference-optimization

Q8_0Excellent
1.4 GB8% of RAMBenchmark needed0.85B params
Run with ToolPiper

General · cooperdk

Q8_0Excellent
1.4 GB8% of RAM~92 tok/sEstimated0.85B params
Run with ToolPiper

Multimodal · dingdust

Q8_0Excellent
1.4 GB8% of RAM~92 tok/sEstimated0.85B params
Run with ToolPiper

Multimodal · yuandaxia

Q8_0Excellent
1.4 GB8% of RAM~92 tok/sEstimated0.85B params
Run with ToolPiper

General · dingdust

Q8_0Excellent
1.7 GB9% of RAM~73 tok/sEstimated1.08B params
Run with ToolPiper

General · ermiaazarkhalili

Q8_0Excellent
1.7 GB9% of RAM~73 tok/sEstimated1.08B params
Run with ToolPiper

General · thepradip

Q8_0Excellent
1.7 GB9% of RAM~73 tok/sEstimated1.08B params
Run with ToolPiper

General · marinarosa

Q8_0Excellent
1.7 GB9% of RAM~73 tok/sEstimated1.08B params
Run with ToolPiper

General · marinarosa

Q8_0Excellent
1.7 GB9% of RAM~73 tok/sEstimated1.08B params
Run with ToolPiper

General · ephemeralyou

Q8_0Excellent
1.7 GB9% of RAM~73 tok/sEstimated1.08B params
Run with ToolPiper

General · marinarosa

Q8_0Excellent
1.7 GB9% of RAM~73 tok/sEstimated1.08B params
Run with ToolPiper

General · marinarosa

Q8_0Excellent
1.7 GB9% of RAM~73 tok/sEstimated1.08B params
Run with ToolPiper

General · ewinregirgojr

Q8_0Excellent
1.7 GB9% of RAM~73 tok/sEstimated1.08B params
Run with ToolPiper

Reasoning · healshsj

Q8_0Excellent
1.7 GB9% of RAM~73 tok/sEstimated1.08B params
Run with ToolPiper

General · andrew0425

Q8_0Excellent
1.7 GB9% of RAM~73 tok/sEstimated1.08B params
Run with ToolPiper

General · daremodels

Q8_0Excellent
1.7 GB9% of RAM~73 tok/sEstimated1.08B params
Run with ToolPiper

Measured on the M3 Pro

Nobody has submitted a benchmark on the M3 Pro yet, so every speed on this page is the formula estimate rather than a measured run. The estimate is bandwidth-driven and calibrated against chips that do have data, which makes it a good guide and not a promise.

ToolPiper contributes a result anonymously when you run the benchmark, and the leaderboard shows every chip that already has one.

What comes next

Projection dated 2026-09-08

Apple has not announced any of this. The M7 Max and Ultra are the first parts Apple designed after cancelling a generation to reach them, so extrapolating from the M5 under-represents them. These rows assume LPDDR6, whose wider channels grow every bus by half, at its top speed bin by the time the Max and Ultra ship. The 1.5 TB Ultra ceiling is Bloomberg's reported design target, and whether that configuration ships depends on the memory market. Stacked memory or a new package fabric would land above these numbers; nobody outside Apple can price that yet.

M7 ProProjected

Projected chip · expected 2027

691 GB/s · 24 to 96 GB unified memory

18-core CPU · 20 or 24-core GPU · 76 TOPS Neural Engine

Would hold about a 129B model at Q4

Why unified memory is the number that matters

On a PC the model has to fit in GPU VRAM, which is a separate pool from system RAM and usually the smaller of the two. Apple Silicon has one pool. The M3 Pro's 150 GB/s bus is shared by CPU, GPU, and Neural Engine, so a 36 GB machine can hand almost all of that to a model with no copy across a bus.

Apple stopped selling this one, which is exactly why it is interesting. The 16-inch chassis has the most thermal headroom Apple ships in a laptop, so sustained token throughput stays close to the burst figure. A used M3 Pro at 36 GB still gives you 150 GB/s and a hard 47B ceiling, and neither number degrades with age the way a battery does.

Common questions

Can the M3 Pro MacBook Pro 16" run a 70B model?

No. A 70B model at Q4_K_M needs about 46 GB, and the largest M3 Pro MacBook Pro 16" tops out at 36 GB, which leaves about 31 GB for weights. The practical ceiling on this machine is around 47B parameters at Q4.

How much unified memory should I get with the M3 Pro MacBook Pro 16"?

Memory is the only spec that changes what you can run at all. 18 GB holds about a 22B model at Q4; 36 GB holds about 47B. It is soldered, so this is a one-time decision, and it is the upgrade worth paying for before core count.

How fast are local LLMs on the M3 Pro?

Token generation is bandwidth-bound, so M3 Pro throughput scales with its 150 GB/s memory bus. Divide bandwidth by the size of the weights actually read per token to get the ceiling, then expect roughly half of that in practice. A 7B model at Q4 reads about 4 GB per token pass, so the M3 Pro lands in the tens of tokens per second and a 70B model lands in the single digits.

Is a used M3 Pro MacBook Pro 16" still worth buying for local AI?

For inference, the specs that matter do not age: 150 GB/s and up to 36 GB of unified memory are the same numbers today as they were in 2023. A used M3 Pro at the top memory option usually beats a new base-tier machine at the same price on both. Check the battery and the display, not the silicon.

Run these models on your MacBook Pro 16"

ToolPiper downloads, manages, and runs local models on Apple Silicon. Free, and nothing leaves the machine.