← All Mac mini models

Mac mini M4 Pro

The M4 Pro Mac mini runs local models at 273 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.

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 M4 Pro
CPU cores12 or 14
GPU cores16 or 20
Unified memory24, 48, or 64 GB
Memory bandwidth273 GB/s
Neural Engine38 TOPS
Released2024
AvailabilityUsed market

Memory bandwidth is faster than 45% of the Apple Silicon chips shipped in a Mac, against a 1228 GB/s peak.

Its memory ceiling is above 45% 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.

GPU cores

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 · 273 GB/s

6,032 of 6,563 models fit, and 5,271 of them run with headroom rather than as a squeeze.

Largest model at Q4
W2 31B A3B dLLM Base preview · 31.12B
Best all-round pick
Kimi K3 DSpark · Q8_0 · ~64 tok/s

48 GB unified memory

42 GB usable for weights · 273 GB/s

6,273 of 6,563 models fit, and 6,033 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
Kimi K3 DSpark · Q8_0 · ~64 tok/s

64 GB unified memory

56 GB usable for weights · 273 GB/s

6,357 of 6,563 models fit, and 6,086 of them run with headroom rather than as a squeeze.

Largest model at Q4
Hy3 REAP 48e · 84.02B
Best all-round pick
Kimi K3 DSpark · Q8_0 · ~64 tok/s

What a 24 GB M4 Pro Mac mini can run

Every model in the database against this exact configuration, at 273 GB/s. Ratings and speeds are the same numbers the model pages show.

Showing 6563 of 6563 models

General · radixark · 2026-07-27

Q8_0Excellent
3.0 GB13% of RAM~64 tok/sEstimated2.25B params
Run with ToolPiper

General · openbmb · 2026-05-21

Q8_0Excellent
1.7 GB7% of RAM~132 tok/sEstimated1.08B params
Run with ToolPiper

General · farbodtavakkoli · 2026-06-17

Q8_0Excellent
10.8 GB45% of RAMBenchmark needed9.23B params
Run with ToolPiper

General · Liquid AI · 2026-05-28

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

General · Liquid AI · 2026-06-24

Q8_0Excellent
0.8 GB3% of RAM~622 tok/sEstimated0.23B params
Run with ToolPiper

General · goekdeniz-guelmez · 2026-07-31

Q8_0Excellent
3.0 GB13% of RAM~63 tok/sEstimated2.27B params
Run with ToolPiper

General · ktruestory · 2026-05-28

Q8_0Excellent
1.7 GB7% of RAM~132 tok/sEstimated1.08B params
Run with ToolPiper

General · petrouil · 2026-07-23

Q8_0Excellent
3.4 GB14% of RAMBenchmark needed2.61B params
Run with ToolPiper

General · weiboai · 2026-06-12

Q8_0Excellent
3.9 GB16% of RAM~46 tok/sEstimated3.09B params
Run with ToolPiper

General · Liquid AI · 2026-07-28

Q8_0Excellent
3.5 GB15% of RAM~53 tok/sEstimated2.7B params
Run with ToolPiper

General · ma7ee7 · 2026-07-30

Q8_0Excellent
4.0 GB17% of RAM~46 tok/sEstimated3.13B params
Run with ToolPiper

Multimodal · Alibaba · 2026-02-28

Q8_0Excellent
1.5 GB6% of RAM~164 tok/sEstimated0.87B params
Run with ToolPiper

Multimodal · Alibaba · 2026-02-28

Q8_0Excellent
3.0 GB13% of RAM~63 tok/sEstimated2.27B params
Run with ToolPiper

Multimodal · Alibaba · 2026-02-28

Q8_0Excellent
1.5 GB6% of RAM~164 tok/sEstimated0.87B params
Run with ToolPiper

Multimodal · Alibaba · 2026-02-28

Q8_0Excellent
3.0 GB13% of RAM~63 tok/sEstimated2.27B params
Run with ToolPiper

General · internscience · 2026-07-13

Q8_0Excellent
5.6 GB23% of RAM~31 tok/sEstimated4.54B params
Run with ToolPiper

Multimodal · ibm-granite · 2026-04-16

Q8_0Excellent
5.0 GB21% of RAM~36 tok/sEstimated4B params
Run with ToolPiper

General · Liquid AI · 2026-03-31

Q8_0Excellent
0.9 GB4% of RAM~409 tok/sEstimated0.35B params
Run with ToolPiper

General · nanbeige · 2026-07-21

Q8_0Excellent
5.2 GB21% of RAM~34 tok/sEstimated4.17B params
Run with ToolPiper

General · cagrigungor · 2026-08-06

Q8_0Excellent
0.8 GB3% of RAM~530 tok/sEstimated0.27B params
Run with ToolPiper

General · ibm-granite · 2026-04-06

Q8_0Excellent
4.3 GB18% of RAM~42 tok/sEstimated3.4B params
Run with ToolPiper

Multimodal · Liquid AI · 2026-01-05

Q8_0Excellent
2.3 GB10% of RAM~89 tok/sEstimated1.6B params
Run with ToolPiper

General · Liquid AI · 2026-01-20

Q8_0Excellent
1.8 GB8% of RAM~122 tok/sEstimated1.17B params
Run with ToolPiper

Reasoning · openonerec · 2026-06-09

Q8_0Excellent
1.4 GB6% of RAM~179 tok/sEstimated0.8B params
Run with ToolPiper

General · Liquid AI · 2026-01-05

Q8_0Excellent
1.8 GB8% of RAM~122 tok/sEstimated1.17B params
Run with ToolPiper

General · Liquid AI · 2026-01-04

Q8_0Excellent
1.8 GB8% of RAM~122 tok/sEstimated1.17B params
Run with ToolPiper

General · Liquid AI · 2026-01-05

Q8_0Excellent
3.4 GB14% of RAM~56 tok/sEstimated2.57B params
Run with ToolPiper

Multimodal · Alibaba · 2026-02-27

Q8_0Excellent
5.7 GB24% of RAM~31 tok/sEstimated4.66B params
Run with ToolPiper

Multimodal · Alibaba · 2026-02-27

Q8_0Excellent
5.7 GB24% of RAM~31 tok/sEstimated4.66B params
Run with ToolPiper

General · Liquid AI · 2025-10-28

Q8_0Excellent
0.9 GB4% of RAM~409 tok/sEstimated0.35B params
Run with ToolPiper

General · ai21labs · 2026-01-06

Q8_0Excellent
3.9 GB16% of RAMBenchmark needed3.03B params
Run with ToolPiper

General · nvidia · 2026-03-02

Q8_0Excellent
4.8 GB20% of RAM~37 tok/sEstimated3.83B params
Run with ToolPiper

General · Liquid AI · 2025-12-25

Q8_0Excellent
3.4 GB14% of RAM~56 tok/sEstimated2.57B params
Run with ToolPiper

General · frontiersmind · 2026-08-03

Q8_0Excellent
1.2 GB5% of RAM~220 tok/sEstimated0.65B params
Run with ToolPiper

Multimodal · davidau · 2026-02-02

Q8_0Excellent
5.3 GB22% of RAM~33 tok/sEstimated4.3B params
Run with ToolPiper

Multimodal · Google · 2026-03-02

Q8_0Excellent
6.2 GB26% of RAM~28 tok/sEstimated5.12B params
Run with ToolPiper

Chat · Liquid AI · 2026-01-06

Q8_0Excellent
1.8 GB8% of RAM~122 tok/sEstimated1.17B params
Run with ToolPiper

General · ibm-granite · 2025-09-16

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

Multimodal · Liquid AI · 2025-08-12

Q8_0Excellent
1.0 GB4% of RAM~318 tok/sEstimated0.45B params
Run with ToolPiper

General · openonerec · 2025-12-30

Q8_0Excellent
2.9 GB12% of RAM~67 tok/sEstimated2.13B params
Run with ToolPiper

General · bytedance · 2025-10-28

Q8_0Excellent
2.1 GB9% of RAM~100 tok/sEstimated1.43B params
Run with ToolPiper

General · Liquid AI · 2025-10-07

Q8_0Excellent
9.8 GB41% of RAMBenchmark needed8.34B params
Run with ToolPiper

Multimodal · Liquid AI · 2025-08-12

Q8_0Excellent
2.3 GB9% of RAM~91 tok/sEstimated1.58B params
Run with ToolPiper

Multimodal · Liquid AI · 2025-10-22

Q8_0Excellent
3.8 GB16% of RAM~48 tok/sEstimated3B params
Run with ToolPiper

General · Liquid AI · 2025-09-22

Q8_0Excellent
3.4 GB14% of RAM~56 tok/sEstimated2.57B params
Run with ToolPiper

General · Liquid AI · 2025-09-30

Q8_0Excellent
0.9 GB4% of RAM~409 tok/sEstimated0.35B params
Run with ToolPiper

General · Liquid AI · 2025-08-22

Q8_0Excellent
1.8 GB8% of RAM~122 tok/sEstimated1.17B params
Run with ToolPiper

General · Liquid AI · 2025-09-03

Q8_0Excellent
0.9 GB4% of RAM~409 tok/sEstimated0.35B params
Run with ToolPiper

General · Liquid AI · 2025-09-03

Q8_0Excellent
1.8 GB8% of RAM~122 tok/sEstimated1.17B params
Run with ToolPiper

General · Liquid AI · 2025-08-25

Q8_0Excellent
0.9 GB4% of RAM~409 tok/sEstimated0.35B params
Run with ToolPiper

General · Liquid AI · 2025-09-03

Q8_0Excellent
0.9 GB4% of RAM~409 tok/sEstimated0.35B params
Run with ToolPiper

General · Liquid AI · 2025-09-03

Q8_0Excellent
1.8 GB8% of RAM~122 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

General · hmellor · 2025-07-22

Q8_0Excellent
1.9 GB8% of RAM~115 tok/sEstimated1.24B params
Run with ToolPiper

General · ibm-granite · 2025-04-30

Q8_0Excellent
7.9 GB33% of RAMBenchmark needed6.67B params
Run with ToolPiper

General · Liquid AI · 2025-07-10

Q8_0Excellent
1.8 GB8% of RAM~122 tok/sEstimated1.17B params
Run with ToolPiper

General · ibm-granite · 2025-09-16

Q8_0Excellent
4.3 GB18% of RAM~42 tok/sEstimated3.4B params
Run with ToolPiper

General · amd · 2025-05-17

Q8_0Excellent
2.2 GB9% of RAM~95 tok/sEstimated1.5B params
Run with ToolPiper

General · stefanruseti · 2025-06-04

Q8_0Excellent
1.9 GB8% of RAM~115 tok/sEstimated1.24B params
Run with ToolPiper

General · ibm-granite · 2025-09-16

Q8_0Excellent
4.1 GB17% of RAM~45 tok/sEstimated3.19B params
Run with ToolPiper

General · lgai-exaone · 2025-07-11

Q8_0Excellent
1.9 GB8% of RAM~112 tok/sEstimated1.28B params
Run with ToolPiper

General · Liquid AI · 2025-07-10

Q8_0Excellent
0.9 GB4% of RAM~409 tok/sEstimated0.35B params
Run with ToolPiper

General · Liquid AI · 2025-07-10

Q8_0Excellent
1.3 GB6% of RAM~193 tok/sEstimated0.74B params
Run with ToolPiper

Multimodal · NCAI · 2025-12-29

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

General · typhoon-ai · 2025-09-23

Q8_0Excellent
5.0 GB21% of RAM~36 tok/sEstimated4.02B params
Run with ToolPiper

General · Alibaba · 2025-08-05

Q8_0Excellent
5.0 GB21% of RAM~36 tok/sEstimated4.02B params
Run with ToolPiper

General · Alibaba · 2025-09-23

Q8_0Excellent
1.3 GB6% of RAM~191 tok/sEstimated0.75B params
Run with ToolPiper

Reasoning · Microsoft · 2025-04-29

Q8_0Excellent
4.8 GB20% of RAM~37 tok/sEstimated3.84B params
Run with ToolPiper

General · pfnet · 2025-02-05

Q8_0Excellent
1.9 GB8% of RAM~111 tok/sEstimated1.29B params
Run with ToolPiper

General · bytedance-seed · 2025-04-09

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

General · sapientinc · 2026-05-17

Q8_0Excellent
1.8 GB8% of RAM~121 tok/sEstimated1.18B params
Run with ToolPiper

General · z-lab · 2026-01-04

Q8_0Excellent
5.0 GB21% of RAM~36 tok/sEstimated4B params
Run with ToolPiper

General · ibm-granite · 2025-10-07

Q8_0Excellent
0.9 GB4% of RAM~409 tok/sEstimated0.35B params
Run with ToolPiper

General · fableforge-ai · 2026-07-05

Q8_0Excellent
2.2 GB9% of RAM~93 tok/sEstimated1.54B params
Run with ToolPiper

General · viorikaai-org · 2026-07-05

Q8_0Excellent
0.6 GB2% of RAM~2,860 tok/sEstimated0.05B params
Run with ToolPiper

Reasoning · jackrong · 2026-03-16

Q8_0Excellent
11.3 GB47% of RAM~15 tok/sEstimated9.65B params
Run with ToolPiper

General · bananamind · 2026-07-17

Q8_0Excellent
0.5 GB2% of RAM~14,300 tok/sEstimated0.01B params
Run with ToolPiper

General · lgai-exaone · 2025-03-12

Q8_0Excellent
3.2 GB13% of RAM~59 tok/sEstimated2.41B params
Run with ToolPiper

General · maliosdark · 2026-07-09

Q8_0Excellent
0.6 GB2% of RAM~2,860 tok/sEstimated0.05B params
Run with ToolPiper

General · raidium · 2026-06-15

Q8_0Excellent
0.5 GB2% of RAM~7,150 tok/sEstimated0.02B params
Run with ToolPiper

Embedding · taide · 2026-06-12

Q8_0Excellent
0.8 GB3% of RAM~477 tok/sEstimated0.3B params
Run with ToolPiper

General · Alibaba · 2025-04-27

Q8_0Excellent
1.3 GB6% of RAM~191 tok/sEstimated0.75B params
Run with ToolPiper

General · Alibaba · 2025-04-27

Q8_0Excellent
2.8 GB12% of RAM~70 tok/sEstimated2.03B params
Run with ToolPiper

Multimodal · zai-org

Q8_0Excellent
2.0 GB8% of RAM~108 tok/sEstimated1.33B params
Run with ToolPiper

Multimodal · Alibaba

Q8_0Excellent
2.9 GB12% of RAM~67 tok/sEstimated2.13B params
Run with ToolPiper

Multimodal · datalab-to

Q8_0Excellent
1.3 GB5% of RAM~207 tok/sEstimated0.69B params
Run with ToolPiper

General · Alibaba · 2025-04-28

Q8_0Excellent
2.4 GB10% of RAM~83 tok/sEstimated1.72B params
Run with ToolPiper

General · huggingfacetb · 2025-07-08

Q8_0Excellent
3.9 GB16% of RAM~46 tok/sEstimated3.08B params
Run with ToolPiper

Multimodal · openbmb

Q8_0Excellent
2.0 GB8% of RAM~110 tok/sEstimated1.3B params
Run with ToolPiper

General · Alibaba · 2025-04-28

Q8_0Excellent
1.2 GB5% of RAM~238 tok/sEstimated0.6B params
Run with ToolPiper

Reasoning · DeepSeek · 2025-01-20

Q8_0Excellent
2.5 GB10% of RAM~80 tok/sEstimated1.78B params
Run with ToolPiper

Multimodal · tencent

Q8_0Excellent
1.7 GB7% of RAMBenchmark needed1.12B params
Run with ToolPiper

General · distil-labs

Q8_0Excellent
0.9 GB4% of RAM~409 tok/sEstimated0.35B params
Run with ToolPiper

General · farbodtavakkoli

Q8_0Excellent
1.8 GB8% of RAM~118 tok/sEstimated1.21B params
Run with ToolPiper

Multimodal · raxcore-dev

Q8_0Excellent
3.0 GB13% of RAM~63 tok/sEstimated2.27B params
Run with ToolPiper

General · huggingfacetb · 2025-06-19

Q8_0Excellent
3.9 GB16% of RAM~46 tok/sEstimated3.08B params
Run with ToolPiper

General · jinaai

Q8_0Excellent
2.2 GB9% of RAM~93 tok/sEstimated1.54B params
Run with ToolPiper

Multimodal · ath-maas

Q8_0Excellent
1.4 GB6% of RAM~168 tok/sEstimated0.85B params
Run with ToolPiper

Multimodal · Alibaba

Q8_0Excellent
2.9 GB12% of RAM~67 tok/sEstimated2.13B params
Run with ToolPiper

Multimodal · Liquid AI

Q8_0Excellent
1.0 GB4% of RAM~318 tok/sEstimated0.45B params
Run with ToolPiper

Reasoning · typhoon-ai

Q8_0Excellent
2.9 GB12% of RAM~67 tok/sEstimated2.13B params
Run with ToolPiper

Multimodal · paddlepaddle

Q8_0Excellent
1.6 GB7% of RAM~149 tok/sEstimated0.96B params
Run with ToolPiper

General · Liquid AI

Q8_0Excellent
0.9 GB4% of RAM~409 tok/sEstimated0.35B params
Run with ToolPiper

Chat · uzlm · 2025-09-03

Q8_0Excellent
1.9 GB8% of RAM~115 tok/sEstimated1.24B params
Run with ToolPiper

Multimodal · paddlepaddle

Q8_0Excellent
1.6 GB7% of RAM~149 tok/sEstimated0.96B params
Run with ToolPiper

General · adamlucek

Q8_0Excellent
1.9 GB8% of RAM~115 tok/sEstimated1.24B params
Run with ToolPiper

Coding · shahriarferdoush

Q8_0Excellent
1.9 GB8% of RAM~115 tok/sEstimated1.24B params
Run with ToolPiper

General · ahczhg

Q8_0Excellent
1.9 GB8% of RAM~115 tok/sEstimated1.24B params
Run with ToolPiper

General · onnx-community · 2025-04-28

Q8_0Excellent
1.0 GB4% of RAM~318 tok/sEstimated0.45B params
Run with ToolPiper

General · etherll

Q8_0Excellent
1.3 GB6% of RAM~193 tok/sEstimated0.74B params
Run with ToolPiper

General · baidu

Q8_0Excellent
0.9 GB4% of RAM~397 tok/sEstimated0.36B params
Run with ToolPiper

General · Liquid AI

Q8_0Excellent
1.8 GB8% of RAM~122 tok/sEstimated1.17B params
Run with ToolPiper

General · openbmb

Q8_0Excellent
1.7 GB7% of RAM~132 tok/sEstimated1.08B params
Run with ToolPiper

Multimodal · lkhl

Q8_0Excellent
2.7 GB11% of RAM~73 tok/sEstimated1.96B params
Run with ToolPiper

Multimodal · infly

Q8_0Excellent
3.0 GB12% of RAM~65 tok/sEstimated2.21B params
Run with ToolPiper

General · benjamin

Q8_0Excellent
1.7 GB7% of RAM~134 tok/sEstimated1.07B params
Run with ToolPiper

General · lemonelabs

Q8_0Excellent
1.8 GB8% of RAM~118 tok/sEstimated1.21B params
Run with ToolPiper

General · openbmb · 2025-06-05

Q8_0Excellent
1.0 GB4% of RAM~333 tok/sEstimated0.43B params
Run with ToolPiper

General · farbodtavakkoli

Q8_0Excellent
2.5 GB10% of RAMBenchmark needed1.77B params
Run with ToolPiper

General · novachronoai

Q8_0Excellent
1.8 GB8% of RAM~118 tok/sEstimated1.21B params
Run with ToolPiper

Multimodal · paddlepaddle

Q8_0Excellent
1.6 GB7% of RAM~149 tok/sEstimated0.96B params
Run with ToolPiper
Q8_0Excellent
4.0 GB17% of RAM~46 tok/sEstimated3.13B params
Run with ToolPiper

General · kamilamila

Q8_0Excellent
1.2 GB5% of RAM~231 tok/sEstimated0.62B params
Run with ToolPiper

General · launch

Q8_0Excellent
2.5 GB10% of RAM~80 tok/sEstimated1.78B params
Run with ToolPiper

General · arcee-ai

Q8_0Excellent
7.3 GB31% of RAMBenchmark needed6.12B params
Run with ToolPiper
Q8_0Excellent
2.2 GB9% of RAM~95 tok/sEstimated1.5B params
Run with ToolPiper

General · Liquid AI

Q8_0Excellent
1.8 GB8% of RAM~118 tok/sEstimated1.21B params
Run with ToolPiper

General · menlo · 2025-06-25

Q8_0Excellent
5.0 GB21% of RAM~36 tok/sEstimated4.02B params
Run with ToolPiper
Q8_0Excellent
1.7 GB7% of RAM~132 tok/sEstimated1.08B params
Run with ToolPiper

General · agentica-org

Q8_0Excellent
2.5 GB10% of RAM~80 tok/sEstimated1.78B params
Run with ToolPiper

General · novaciano

Q8_0Excellent
2.2 GB9% of RAM~95 tok/sEstimated1.5B params
Run with ToolPiper

General · dmusingu

Q8_0Excellent
2.9 GB12% of RAM~67 tok/sEstimated2.13B params
Run with ToolPiper

General · kgrabko

Q8_0Excellent
2.2 GB9% of RAM~95 tok/sEstimated1.5B params
Run with ToolPiper

General · ordenwills

Q8_0Excellent
0.9 GB4% of RAM~409 tok/sEstimated0.35B params
Run with ToolPiper
Q8_0Excellent
2.1 GB9% of RAM~103 tok/sEstimated1.39B params
Run with ToolPiper

General · carsenk

Q8_0Excellent
1.9 GB8% of RAM~115 tok/sEstimated1.24B params
Run with ToolPiper

Reasoning · nvidia

Q8_0Excellent
2.2 GB9% of RAM~93 tok/sEstimated1.54B params
Run with ToolPiper

Multimodal · zero-point-ai

Q8_0Excellent
3.0 GB13% of RAM~63 tok/sEstimated2.27B params
Run with ToolPiper

General · openbmb

Q8_0Excellent
2.0 GB8% of RAM~110 tok/sEstimated1.3B params
Run with ToolPiper

General · ibm-granite

Q8_0Excellent
2.1 GB9% of RAM~98 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~110 tok/sEstimated1.3B params
Run with ToolPiper

General · tencent

Q8_0Excellent
2.7 GB11% of RAM~73 tok/sEstimated1.96B params
Run with ToolPiper

General · skis-ai-research

Q8_0Excellent
1.8 GB8% of RAM~122 tok/sEstimated1.17B params
Run with ToolPiper

General · menlo

Q8_0Excellent
2.4 GB10% of RAM~83 tok/sEstimated1.72B params
Run with ToolPiper

General · thkim0305

Q8_0Excellent
1.6 GB7% of RAM~143 tok/sEstimated1B params
Run with ToolPiper
Q8_0Excellent
1.5 GB6% of RAM~164 tok/sEstimated0.87B params
Run with ToolPiper

General · huihui-ai

Q8_0Excellent
3.0 GB13% of RAM~63 tok/sEstimated2.27B params
Run with ToolPiper

16-core vs 20-core GPU

Both bins run the same 273 GB/s memory bus, so token generation is the same on either one. The extra cores show up in image and video work, not in tokens per second.

ConfigurationMemory bandwidthMemory optionsModels that fit
12-core CPU, 16-core GPU273 GB/s24, 48, 64 GBIdentical
14-core CPU, 20-core GPU273 GB/s24, 48, 64 GBIdentical

Measured on the M4 Pro

Nobody has submitted a benchmark on the M4 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 M4 Pro's 273 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.

Apple stopped selling this one, which is exactly why it is interesting. The mini is the cheapest way onto this chip, and it runs headless on a shelf perfectly well. Nothing about local inference needs the display attached. A used M4 Pro at 64 GB still gives you 273 GB/s and a hard 85B ceiling, and neither number degrades with age the way a battery does.

Common questions

Can the M4 Pro Mac mini 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 M4 Pro Mac mini?

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 M4 Pro?

Token generation is bandwidth-bound, so M4 Pro throughput scales with its 273 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 M4 Pro lands in the tens of tokens per second and a 70B model lands in the single digits.

Is the 20-core GPU worth it over the 16-core on the M4 Pro?

Not for LLMs. Both bins run the same 273 GB/s memory bus and take the same memory options, and token generation is bound by bandwidth rather than GPU cores. The extra cores show up in image generation and video work, not in tokens per second.

Is a used M4 Pro Mac mini still worth buying for local AI?

For inference, the specs that matter do not age: 273 GB/s and up to 64 GB of unified memory are the same numbers today as they were in 2024. A used M4 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 Mac mini

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