← All MacBook Pro 16" models

MacBook Pro 16" M5 Pro

The M5 Pro MacBook Pro 16" runs local models at 307 GB/s of memory bandwidth with 24 to 64 GB of unified memory. On Apple Silicon that memory is shared with the GPU, so the whole pool is available for weights: at 64 GB you can hold roughly a 85B 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.

Specifications

ChipApple M5 Pro
CPU cores18
GPU cores20
Unified memory24, 48, or 64 GB
Memory bandwidth307 GB/s
Neural Engine38 TOPS
Released2026
AvailabilitySold new by Apple

Memory bandwidth is faster than 50% of the Apple Silicon chips shipped in a Mac, against a 819 GB/s peak.

Its memory ceiling is above 44% 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.

24 GB unified memory

21 GB usable for weights · 307 GB/s

3,352 of 3,641 models fit, and 3,007 of them run with headroom rather than as a squeeze.

Largest model at Q4
Qwen3 VL 30B A3B Instruct · 31.07B
Best all-round pick
Qwen3.5 0.8B · Q8_0 · ~185 tok/s

48 GB unified memory

42 GB usable for weights · 307 GB/s

3,503 of 3,641 models fit, and 3,351 of them run with headroom rather than as a squeeze.

Largest model at Q4
Yi 34Bx2 MoE 60B DPO · 60.81B
Best all-round pick
Qwen3.5 0.8B · Q8_0 · ~185 tok/s

64 GB unified memory

56 GB usable for weights · 307 GB/s

3,541 of 3,641 models fit, and 3,385 of them run with headroom rather than as a squeeze.

Largest model at Q4
Kimi K2.6 JANGTQ_3L · 83.44B
Best all-round pick
Qwen3.5 0.8B · Q8_0 · ~185 tok/s

What a 24 GB M5 Pro MacBook Pro 16" can run

Every model in the database against this exact configuration, at 307 GB/s. Ratings and speeds are the same numbers the model pages show.

Showing 3641 of 3641 models

Multimodal · Alibaba · 2026-02-28

Q8_0Excellent
1.5 GB6% of RAM~185 tok/sEstimated0.87B params
Run with ToolPiper

Multimodal · Alibaba · 2026-02-28

Q8_0Excellent
3.0 GB13% of RAM~71 tok/sEstimated2.27B params
Run with ToolPiper

Multimodal · Alibaba · 2026-02-28

Q8_0Excellent
1.5 GB6% of RAM~185 tok/sEstimated0.87B params
Run with ToolPiper

Multimodal · Alibaba · 2026-02-28

Q8_0Excellent
3.0 GB13% of RAM~71 tok/sEstimated2.27B params
Run with ToolPiper

Multimodal · Alibaba · 2026-02-27

Q8_0Excellent
5.7 GB24% of RAM~35 tok/sEstimated4.66B params
Run with ToolPiper

Multimodal · Alibaba · 2026-02-27

Q8_0Excellent
5.7 GB24% of RAM~35 tok/sEstimated4.66B params
Run with ToolPiper

General · Liquid AI · 2025-11-28

Q8_0Excellent
1.8 GB8% of RAM~137 tok/sEstimated1.17B params
Run with ToolPiper

General · Liquid AI · 2025-11-28

Q8_0Excellent
0.9 GB4% of RAM~459 tok/sEstimated0.35B params
Run with ToolPiper

Reasoning · Liquid AI · 2025-11-28

Q8_0Excellent
1.8 GB8% of RAM~137 tok/sEstimated1.17B params
Run with ToolPiper

General · Liquid AI · 2025-11-28

Q8_0Excellent
9.8 GB41% of RAMBenchmark needed8.3B params
Run with ToolPiper

General · Liquid AI · 2025-11-28

Q8_0Excellent
1.8 GB8% of RAM~137 tok/sEstimated1.17B params
Run with ToolPiper

General · Liquid AI · 2025-11-28

Q8_0Excellent
0.9 GB4% of RAM~459 tok/sEstimated0.35B params
Run with ToolPiper

General · Liquid AI · 2025-11-28

Q8_0Excellent
3.4 GB14% of RAM~63 tok/sEstimated2.57B params
Run with ToolPiper

General · Liquid AI · 2025-11-28

Q8_0Excellent
1.3 GB6% of RAM~217 tok/sEstimated0.74B params
Run with ToolPiper

General · Liquid AI · 2025-11-28

Q8_0Excellent
1.8 GB8% of RAM~137 tok/sEstimated1.17B params
Run with ToolPiper

General · Liquid AI · 2025-11-28

Q8_0Excellent
0.9 GB4% of RAM~459 tok/sEstimated0.35B params
Run with ToolPiper

General · Liquid AI · 2025-11-28

Q8_0Excellent
3.4 GB14% of RAM~63 tok/sEstimated2.57B params
Run with ToolPiper

General · Liquid AI · 2025-11-28

Q8_0Excellent
0.9 GB4% of RAM~459 tok/sEstimated0.35B params
Run with ToolPiper

General · Liquid AI · 2025-11-28

Q8_0Excellent
1.8 GB8% of RAM~137 tok/sEstimated1.17B params
Run with ToolPiper

General · Liquid AI · 2025-11-28

Q8_0Excellent
0.9 GB4% of RAM~459 tok/sEstimated0.35B params
Run with ToolPiper

General · Liquid AI · 2025-11-28

Q8_0Excellent
1.8 GB8% of RAM~137 tok/sEstimated1.17B params
Run with ToolPiper

Reasoning · Liquid AI · 2025-11-28

Q8_0Excellent
0.9 GB4% of RAM~459 tok/sEstimated0.35B params
Run with ToolPiper

General · ibm-granite · 2025-09-16

Q8_0Excellent
8.2 GB34% of RAMBenchmark needed6.94B params
Run with ToolPiper

Chat · Liquid AI · 2025-11-28

Q8_0Excellent
1.8 GB8% of RAM~137 tok/sEstimated1.17B params
Run with ToolPiper

Chat · Liquid AI · 2025-11-28

Q8_0Excellent
3.4 GB14% of RAM~63 tok/sEstimated2.57B params
Run with ToolPiper

Chat · Liquid AI · 2025-11-28

Q8_0Excellent
1.8 GB8% of RAM~137 tok/sEstimated1.17B params
Run with ToolPiper

General · NCAI · 2025-12-29

Q8_0Excellent
8.6 GB36% of RAMBenchmark needed7.25B params
Run with ToolPiper

Reasoning · HuggingFace · 2025-07-08

Q8_0Excellent
3.8 GB16% of RAM~54 tok/sEstimated3B params
Run with ToolPiper

General · ibm-granite · 2025-09-16

Q8_0Excellent
4.1 GB17% of RAM~50 tok/sEstimated3.19B params
Run with ToolPiper

General · Liquid AI · 2025-11-28

Q8_0Excellent
2.2 GB9% of RAM~107 tok/sEstimated1.5B params
Run with ToolPiper

General · Liquid AI · 2025-11-28

Q8_0Excellent
2.2 GB9% of RAM~107 tok/sEstimated1.5B params
Run with ToolPiper

Multimodal · NCAI · 2025-12-29

Q8_0Excellent
9.0 GB37% of RAMBenchmark needed7.58B params
Run with ToolPiper

Multimodal · Google · 2025-07-30

Q8_0Excellent
6.2 GB26% of RAM~32 tok/sEstimated5.1B params
Run with ToolPiper

Multimodal · Google · 2025-06-25

Q8_0Excellent
5.0 GB21% of RAM~40 tok/sEstimated4B params
Run with ToolPiper

Multimodal · Liquid AI · 2025-11-28

Q8_0Excellent
1.0 GB4% of RAM~357 tok/sEstimated0.45B params
Run with ToolPiper

Multimodal · Liquid AI · 2025-11-28

Q8_0Excellent
2.3 GB10% of RAM~101 tok/sEstimated1.6B params
Run with ToolPiper

Multimodal · Liquid AI · 2025-11-28

Q8_0Excellent
3.8 GB16% of RAM~54 tok/sEstimated3B params
Run with ToolPiper

Multimodal · Liquid AI · 2025-11-28

Q8_0Excellent
2.3 GB9% of RAM~102 tok/sEstimated1.58B params
Run with ToolPiper

Reasoning · jackrong · 2026-03-16

Q8_0Excellent
11.3 GB47% of RAM~17 tok/sEstimated9.65B params
Run with ToolPiper

General · lgai-exaone · 2025-03-12

Q8_0Excellent
3.2 GB13% of RAM~67 tok/sEstimated2.41B params
Run with ToolPiper

General · LG AI · 2025-07-15

Q8_0Excellent
1.8 GB8% of RAM~134 tok/sEstimated1.2B params
Run with ToolPiper

General · raidium · 2026-06-15

Q8_0Excellent
0.5 GB2% of RAM~8,040 tok/sEstimated0.02B params
Run with ToolPiper

Embedding · taide · 2026-06-12

Q8_0Excellent
0.8 GB3% of RAM~536 tok/sEstimated0.3B params
Run with ToolPiper

General · Alibaba · 2025-04-27

Q8_0Excellent
1.3 GB6% of RAM~214 tok/sEstimated0.75B params
Run with ToolPiper

General · Alibaba · 2025-04-27

Q8_0Excellent
2.8 GB12% of RAM~79 tok/sEstimated2.03B params
Run with ToolPiper

Multimodal · zai-org

Q8_0Excellent
2.0 GB8% of RAM~121 tok/sEstimated1.33B params
Run with ToolPiper

Multimodal · Alibaba

Q8_0Excellent
2.9 GB12% of RAM~75 tok/sEstimated2.13B params
Run with ToolPiper

General · Alibaba

Q8_0Excellent
2.2 GB9% of RAM~104 tok/sEstimated1.54B params
Run with ToolPiper

General · Alibaba

Q8_0Excellent
1.0 GB4% of RAM~328 tok/sEstimated0.49B params
Run with ToolPiper

Multimodal · openbmb

Q8_0Excellent
2.0 GB8% of RAM~124 tok/sEstimated1.3B params
Run with ToolPiper

Reasoning · DeepSeek

Q8_0Excellent
2.5 GB10% of RAM~90 tok/sEstimated1.78B params
Run with ToolPiper

Multimodal · rednote-hilab

Q8_0Excellent
3.9 GB16% of RAM~53 tok/sEstimated3.04B params
Run with ToolPiper

Multimodal · datalab-to

Q8_0Excellent
1.3 GB5% of RAM~233 tok/sEstimated0.69B params
Run with ToolPiper

General · openbmb

Q8_0Excellent
1.7 GB7% of RAM~149 tok/sEstimated1.08B params
Run with ToolPiper

Multimodal · rednote-hilab

Q8_0Excellent
3.9 GB16% of RAM~53 tok/sEstimated3.04B params
Run with ToolPiper

General · hmellor

Q8_0Excellent
1.9 GB8% of RAM~130 tok/sEstimated1.24B params
Run with ToolPiper

General · distil-labs

Q8_0Excellent
0.9 GB4% of RAM~459 tok/sEstimated0.35B params
Run with ToolPiper

General · farbodtavakkoli

Q8_0Excellent
1.8 GB8% of RAM~133 tok/sEstimated1.21B params
Run with ToolPiper

General · Liquid AI

Q8_0Excellent
9.9 GB41% of RAMBenchmark needed8.47B params
Run with ToolPiper

General · ibm-granite

Q8_0Excellent
7.9 GB33% of RAMBenchmark needed6.67B params
Run with ToolPiper
Q8_0Excellent
0.5 GB2% of RAM~16,081 tok/sEstimated0.01B params
Run with ToolPiper

Multimodal · lkhl

Q8_0Excellent
2.7 GB11% of RAM~82 tok/sEstimated1.96B params
Run with ToolPiper

General · jinaai

Q8_0Excellent
2.2 GB9% of RAM~104 tok/sEstimated1.54B params
Run with ToolPiper

General · Alibaba

Q8_0Excellent
2.9 GB12% of RAM~75 tok/sEstimated2.13B params
Run with ToolPiper

Reasoning · typhoon-ai

Q8_0Excellent
2.9 GB12% of RAM~75 tok/sEstimated2.13B params
Run with ToolPiper

General · Upstage

Q8_0Excellent
9.5 GB40% of RAMBenchmark needed8.05B params
Run with ToolPiper

General · openai

Q8_0Excellent
3.1 GB13% of RAMBenchmark needed2.37B params
Run with ToolPiper

General · paddlepaddle

Q8_0Excellent
1.6 GB7% of RAM~168 tok/sEstimated0.96B params
Run with ToolPiper

General · Liquid AI

Q8_0Excellent
0.9 GB4% of RAM~459 tok/sEstimated0.35B params
Run with ToolPiper

General · pfnet

Q8_0Excellent
1.9 GB8% of RAM~125 tok/sEstimated1.29B params
Run with ToolPiper

General · openbmb

Q8_0Excellent
1.7 GB7% of RAM~149 tok/sEstimated1.08B params
Run with ToolPiper

General · baidu

Q8_0Excellent
0.9 GB4% of RAM~447 tok/sEstimated0.36B params
Run with ToolPiper

General · amd

Q8_0Excellent
2.2 GB9% of RAM~107 tok/sEstimated1.5B params
Run with ToolPiper

General · bytedance-seed

Q8_0Excellent
11.0 GB46% of RAMBenchmark needed9.37B params
Run with ToolPiper

General · arcee-ai

Q8_0Excellent
7.3 GB31% of RAMBenchmark needed6.12B params
Run with ToolPiper

General · adamlucek

Q8_0Excellent
1.9 GB8% of RAM~130 tok/sEstimated1.24B params
Run with ToolPiper

Coding · shahriarferdoush

Q8_0Excellent
1.9 GB8% of RAM~130 tok/sEstimated1.24B params
Run with ToolPiper

General · ahczhg

Q8_0Excellent
1.9 GB8% of RAM~130 tok/sEstimated1.24B params
Run with ToolPiper

General · abaryan

Q8_0Excellent
1.9 GB8% of RAM~130 tok/sEstimated1.24B params
Run with ToolPiper

General · etherll

Q8_0Excellent
1.3 GB6% of RAM~217 tok/sEstimated0.74B params
Run with ToolPiper

General · farbodtavakkoli

Q8_0Excellent
2.5 GB10% of RAMBenchmark needed1.77B params
Run with ToolPiper
Q8_0Excellent
4.0 GB17% of RAM~51 tok/sEstimated3.13B params
Run with ToolPiper

General · kamilamila

Q8_0Excellent
1.2 GB5% of RAM~259 tok/sEstimated0.62B params
Run with ToolPiper
Q8_0Excellent
2.2 GB9% of RAM~107 tok/sEstimated1.5B params
Run with ToolPiper

General · paddlepaddle

Q8_0Excellent
1.6 GB7% of RAM~168 tok/sEstimated0.96B params
Run with ToolPiper

General · agentica-org

Q8_0Excellent
2.5 GB10% of RAM~90 tok/sEstimated1.78B params
Run with ToolPiper

General · novaciano

Q8_0Excellent
2.2 GB9% of RAM~107 tok/sEstimated1.5B params
Run with ToolPiper

General · dmusingu

Q8_0Excellent
2.9 GB12% of RAM~75 tok/sEstimated2.13B params
Run with ToolPiper

General · kgrabko

Q8_0Excellent
2.2 GB9% of RAM~107 tok/sEstimated1.5B params
Run with ToolPiper

General · ordenwills

Q8_0Excellent
0.9 GB4% of RAM~459 tok/sEstimated0.35B params
Run with ToolPiper
Q8_0Excellent
2.1 GB9% of RAM~116 tok/sEstimated1.39B params
Run with ToolPiper

General · carsenk

Q8_0Excellent
1.9 GB8% of RAM~130 tok/sEstimated1.24B params
Run with ToolPiper

Reasoning · nvidia

Q8_0Excellent
2.2 GB9% of RAM~104 tok/sEstimated1.54B params
Run with ToolPiper

General · zero-point-ai

Q8_0Excellent
3.0 GB13% of RAM~71 tok/sEstimated2.27B params
Run with ToolPiper

General · ibm-granite

Q8_0Excellent
2.0 GB8% of RAMBenchmark needed1.33B params
Run with ToolPiper

General · openbmb

Q8_0Excellent
2.0 GB8% of RAM~124 tok/sEstimated1.3B params
Run with ToolPiper

General · ibm-granite

Q8_0Excellent
2.1 GB9% of RAM~110 tok/sEstimated1.46B params
Run with ToolPiper

General · osaurusai

Q8_0Excellent
11.3 GB47% of RAMBenchmark needed9.65B params
Run with ToolPiper

General · pyoakum

Q8_0Excellent
6.5 GB27% of RAMBenchmark needed5.35B params
Run with ToolPiper

General · ibm-granite

Q8_0Excellent
4.2 GB17% of RAMBenchmark needed3.3B params
Run with ToolPiper
Q8_0Excellent
2.0 GB8% of RAM~124 tok/sEstimated1.3B params
Run with ToolPiper

General · tencent

Q8_0Excellent
2.7 GB11% of RAM~82 tok/sEstimated1.96B params
Run with ToolPiper

General · skis-ai-research

Q8_0Excellent
1.8 GB8% of RAM~137 tok/sEstimated1.17B params
Run with ToolPiper

General · menlo

Q8_0Excellent
2.4 GB10% of RAM~93 tok/sEstimated1.72B params
Run with ToolPiper

General · thkim0305

Q8_0Excellent
1.6 GB7% of RAM~161 tok/sEstimated1B params
Run with ToolPiper

General · magistrtheone

Q8_0Excellent
11.5 GB48% of RAMBenchmark needed9.87B params
Run with ToolPiper
Q8_0Excellent
1.5 GB6% of RAM~185 tok/sEstimated0.87B params
Run with ToolPiper

General · huihui-ai

Q8_0Excellent
3.0 GB13% of RAM~71 tok/sEstimated2.27B params
Run with ToolPiper

Coding · rahul7star

Q8_0Excellent
1.5 GB6% of RAM~185 tok/sEstimated0.87B params
Run with ToolPiper

General · inclusionai

Q8_0Excellent
3.2 GB13% of RAM~66 tok/sEstimated2.44B params
Run with ToolPiper

General · TII

Q8_0Excellent
2.2 GB9% of RAM~104 tok/sEstimated1.55B params
Run with ToolPiper

Coding · z-lab

Q8_0Excellent
1.7 GB7% of RAM~149 tok/sEstimated1.08B params
Run with ToolPiper
Q8_0Excellent
6.9 GB29% of RAMBenchmark needed5.75B params
Run with ToolPiper

General · artificialguybr

Q8_0Excellent
1.9 GB8% of RAM~130 tok/sEstimated1.24B params
Run with ToolPiper

General · Microsoft

Q8_0Excellent
0.7 GB3% of RAMBenchmark needed0.17B params
Run with ToolPiper

General · roystar

Q8_0Excellent
2.2 GB9% of RAM~104 tok/sEstimated1.54B params
Run with ToolPiper

General · weiboai

Q8_0Excellent
2.5 GB10% of RAM~90 tok/sEstimated1.78B params
Run with ToolPiper

General · Microsoft

Q8_0Excellent
0.7 GB3% of RAMBenchmark needed0.17B params
Run with ToolPiper

Reasoning · ai21labs

Q8_0Excellent
4.1 GB17% of RAMBenchmark needed3.2B params
Run with ToolPiper

General · TII

Q8_0Excellent
2.2 GB9% of RAM~104 tok/sEstimated1.55B params
Run with ToolPiper

General · tencent

Q8_0Excellent
1.1 GB5% of RAM~298 tok/sEstimated0.54B params
Run with ToolPiper

General · primeintellect

Q8_0Excellent
1.1 GB5% of RAMBenchmark needed0.54B params
Run with ToolPiper

General · Alibaba · 2025-04-27

Q8_0Excellent
5.0 GB21% of RAM~40 tok/sEstimated4.02B params
Run with ToolPiper

Multimodal · Alibaba · 2026-02-27

Q8_0Excellent
11.3 GB47% of RAM~17 tok/sEstimated9.65B params
Run with ToolPiper

Multimodal · Alibaba

Q8_0Excellent
5.5 GB23% of RAM~36 tok/sEstimated4.44B params
Run with ToolPiper

Multimodal · datalab-to

Q8_0Excellent
6.4 GB27% of RAM~30 tok/sEstimated5.3B params
Run with ToolPiper

Multimodal · Microsoft

Q8_0Excellent
5.1 GB21% of RAM~39 tok/sEstimated4.15B params
Run with ToolPiper

General · ibm-granite

Q8_0Excellent
4.3 GB18% of RAM~47 tok/sEstimated3.4B params
Run with ToolPiper

Multimodal · nanonets

Q8_0Excellent
4.7 GB20% of RAM~43 tok/sEstimated3.75B params
Run with ToolPiper

Multimodal · Alibaba · 2026-02-26

Q8_0Excellent
11.3 GB47% of RAM~17 tok/sEstimated9.65B params
Run with ToolPiper

General · nanonets

Q8_0Excellent
4.7 GB20% of RAM~43 tok/sEstimated3.75B params
Run with ToolPiper

Multimodal · ibm-granite

Q8_0Excellent
5.0 GB21% of RAM~40 tok/sEstimated4B params
Run with ToolPiper

Multimodal · typhoon-ai

Q8_0Excellent
4.7 GB20% of RAM~43 tok/sEstimated3.75B params
Run with ToolPiper

General · internlm

Q8_0Excellent
2.1 GB9% of RAM~115 tok/sEstimated1.4B params
Run with ToolPiper
Q8_0Excellent
5.5 GB23% of RAM~36 tok/sEstimated4.44B params
Run with ToolPiper

General · kristaller486

Q8_0Excellent
3.9 GB16% of RAM~53 tok/sEstimated3.04B params
Run with ToolPiper

General · zstanjj

Q8_0Excellent
4.8 GB20% of RAM~42 tok/sEstimated3.82B params
Run with ToolPiper

General · ibm-granite

Q8_0Excellent
4.3 GB18% of RAM~47 tok/sEstimated3.4B params
Run with ToolPiper

General · weiboai

Q8_0Excellent
3.9 GB16% of RAM~52 tok/sEstimated3.09B params
Run with ToolPiper

General · x-izhang

Q8_0Excellent
4.1 GB17% of RAM~49 tok/sEstimated3.25B params
Run with ToolPiper

General · bytedance

Q8_0Excellent
2.7 GB11% of RAM~80 tok/sEstimated2.01B params
Run with ToolPiper

General · ibm-granite

Q8_0Excellent
4.3 GB18% of RAM~47 tok/sEstimated3.4B params
Run with ToolPiper

General · bytedance

Q8_0Excellent
3.5 GB14% of RAM~60 tok/sEstimated2.67B params
Run with ToolPiper

General · stanford-oval

Q8_0Excellent
4.7 GB20% of RAM~43 tok/sEstimated3.75B params
Run with ToolPiper

General · flowaicom

Q8_0Excellent
4.8 GB20% of RAM~42 tok/sEstimated3.82B params
Run with ToolPiper

General · bllossom

Q8_0Excellent
4.1 GB17% of RAM~50 tok/sEstimated3.21B params
Run with ToolPiper

General · opengvlab

Q8_0Excellent
2.8 GB12% of RAM~77 tok/sEstimated2.09B params
Run with ToolPiper

General · z-lab

Q8_0Excellent
4.4 GB18% of RAM~46 tok/sEstimated3.48B params
Run with ToolPiper

General · bytedance

Q8_0Excellent
2.1 GB9% of RAM~112 tok/sEstimated1.43B params
Run with ToolPiper

General · radheneev

Q8_0Excellent
4.1 GB17% of RAM~50 tok/sEstimated3.21B params
Run with ToolPiper

Measured on the M5 Pro

Nobody has submitted a benchmark on the M5 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.

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 M5 Pro's 307 GB/s bus is shared by CPU, GPU, and Neural Engine, so a 64 GB machine can hand almost all of that to a model with no copy across a bus.

The 16-inch chassis has the most thermal headroom Apple ships in a laptop, so sustained token throughput stays close to the burst figure. Buy the memory, not the cores: every extra GB raises what you can load, while the core count only moves throughput on models that already fit.

Common questions

Can the M5 Pro MacBook Pro 16" run a 70B model?

Yes, at 64 GB. A 70B model at Q4_K_M needs about 46 GB including an 8K context, and 64 GB of unified memory leaves about 56 GB for weights once macOS takes its share. At 24 GB it does not fit at any quantization worth running.

How much unified memory should I get with the M5 Pro MacBook Pro 16"?

Memory is the only spec that changes what you can run at all. 24 GB holds about a 31B model at Q4; 64 GB holds about 85B. 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 M5 Pro?

Token generation is bandwidth-bound, so M5 Pro throughput scales with its 307 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 M5 Pro lands in the tens of tokens per second and a 70B model lands in the single digits.

Should I buy the M5 Pro MacBook Pro 16" now or wait for the next one?

Buy on the memory you need today. Apple raises memory ceilings slowly and bandwidth in steps, and the M5 Pro already holds about a 85B model at Q4. If your target model fits in 64 GB, waiting buys throughput rather than capability.

Run these models on your MacBook Pro 16"

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