← All Mac mini models

Mac mini M6

The M6 Mac mini runs local models at 153 to 170 GB/s of memory bandwidth with 16 to 32 GB of unified memory. On Apple Silicon that memory is shared with the GPU, so the whole pool is available for weights: at 32 GB you can hold roughly a 42B dense model at Q4. A base M chip is the narrow end of the memory bus. It runs small models pleasantly and stops hard at the memory ceiling, which is the constraint you will hit first.

By , Founder & Lead Engineer— Updated

Specifications

ChipApple M6
CPU cores12
GPU cores12
Unified memory16, 24, or 32 GB
Memory bandwidth153 to 170 GB/s
Neural Engine76 TOPS
Released2026
AvailabilitySold new by Apple

Memory bandwidth is faster than 30% of the Apple Silicon chips shipped in a Mac, against a 1228 GB/s peak.

Its memory ceiling is above 15% 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.

16 GB unified memory

14 GB usable for weights · 153 GB/s

5,572 of 6,563 models fit, and 5,054 of them run with headroom rather than as a squeeze.

Largest model at Q4
maple preview · 20.21B
Best all-round pick
MiniCPM5 1B · Q8_0 · ~74 tok/s

24 GB unified memory

21 GB usable for weights · 170 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
MiniCPM5 1B · Q8_0 · ~82 tok/s

32 GB unified memory

28 GB usable for weights · 170 GB/s

6,082 of 6,563 models fit, and 5,571 of them run with headroom rather than as a squeeze.

Largest model at Q4
Phi 3.5 MoE instruct · 41.87B
Best all-round pick
MiniCPM5 1B · Q8_0 · ~82 tok/s

What a 16 GB M6 Mac mini can run

Every model in the database against this exact configuration, at 153 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 GB11% of RAM~74 tok/sEstimated1.08B params
Run with ToolPiper

General · Liquid AI · 2026-06-24

Q8_0Excellent
0.8 GB5% of RAM~348 tok/sEstimated0.23B params
Run with ToolPiper

General · ktruestory · 2026-05-28

Q8_0Excellent
1.7 GB11% of RAM~74 tok/sEstimated1.08B params
Run with ToolPiper

General · petrouil · 2026-07-23

Q8_0Excellent
3.4 GB21% of RAMBenchmark needed2.61B params
Run with ToolPiper

General · Liquid AI · 2026-03-31

Q8_0Excellent
0.9 GB6% of RAM~229 tok/sEstimated0.35B params
Run with ToolPiper

Multimodal · Alibaba · 2026-02-28

Q8_0Excellent
1.5 GB9% of RAM~92 tok/sEstimated0.87B params
Run with ToolPiper

General · radixark · 2026-07-27

Q8_0Excellent
3.0 GB19% of RAM~36 tok/sEstimated2.25B params
Run with ToolPiper

Multimodal · Alibaba · 2026-02-28

Q8_0Excellent
1.5 GB9% of RAM~92 tok/sEstimated0.87B params
Run with ToolPiper

General · goekdeniz-guelmez · 2026-07-31

Q8_0Excellent
3.0 GB19% of RAM~35 tok/sEstimated2.27B params
Run with ToolPiper

General · cagrigungor · 2026-08-06

Q8_0Excellent
0.8 GB5% of RAM~297 tok/sEstimated0.27B params
Run with ToolPiper

Multimodal · Alibaba · 2026-02-28

Q8_0Excellent
3.0 GB19% of RAM~35 tok/sEstimated2.27B params
Run with ToolPiper

Multimodal · Alibaba · 2026-02-28

Q8_0Excellent
3.0 GB19% of RAM~35 tok/sEstimated2.27B params
Run with ToolPiper

General · Liquid AI · 2026-05-28

Q8_0Excellent
9.9 GB62% of RAMBenchmark needed8.47B params
Run with ToolPiper

General · Liquid AI · 2026-07-28

Q8_0Excellent
3.5 GB22% of RAM~30 tok/sEstimated2.7B params
Run with ToolPiper

Multimodal · Liquid AI · 2026-01-05

Q8_0Excellent
2.3 GB14% of RAM~50 tok/sEstimated1.6B params
Run with ToolPiper

General · Liquid AI · 2026-01-20

Q8_0Excellent
1.8 GB11% of RAM~68 tok/sEstimated1.17B params
Run with ToolPiper

Reasoning · openonerec · 2026-06-09

Q8_0Excellent
1.4 GB9% of RAM~100 tok/sEstimated0.8B params
Run with ToolPiper

General · Liquid AI · 2026-01-05

Q8_0Excellent
1.8 GB11% of RAM~68 tok/sEstimated1.17B params
Run with ToolPiper

General · Liquid AI · 2026-01-04

Q8_0Excellent
1.8 GB11% of RAM~68 tok/sEstimated1.17B params
Run with ToolPiper

Chat · Liquid AI · 2026-01-06

Q8_0Excellent
1.8 GB11% of RAM~68 tok/sEstimated1.17B params
Run with ToolPiper

General · Liquid AI · 2025-10-28

Q8_0Excellent
0.9 GB6% of RAM~229 tok/sEstimated0.35B params
Run with ToolPiper

General · frontiersmind · 2026-08-03

Q8_0Excellent
1.2 GB8% of RAM~123 tok/sEstimated0.65B params
Run with ToolPiper

General · farbodtavakkoli · 2026-06-17

Q8_0Excellent
10.8 GB67% of RAMBenchmark needed9.23B params
Run with ToolPiper

General · hmellor · 2025-07-22

Q8_0Excellent
1.9 GB12% of RAM~65 tok/sEstimated1.24B params
Run with ToolPiper

General · ibm-granite · 2025-09-16

Q8_0Excellent
8.2 GB52% of RAMBenchmark needed6.94B params
Run with ToolPiper

Multimodal · Liquid AI · 2025-08-12

Q8_0Excellent
1.0 GB6% of RAM~178 tok/sEstimated0.45B params
Run with ToolPiper

General · Liquid AI · 2025-09-30

Q8_0Excellent
0.9 GB6% of RAM~229 tok/sEstimated0.35B params
Run with ToolPiper

General · Liquid AI · 2025-08-22

Q8_0Excellent
1.8 GB11% of RAM~68 tok/sEstimated1.17B params
Run with ToolPiper

General · Liquid AI · 2025-09-03

Q8_0Excellent
0.9 GB6% of RAM~229 tok/sEstimated0.35B params
Run with ToolPiper

General · Liquid AI · 2025-09-03

Q8_0Excellent
1.8 GB11% of RAM~68 tok/sEstimated1.17B params
Run with ToolPiper

General · Liquid AI · 2025-08-25

Q8_0Excellent
0.9 GB6% of RAM~229 tok/sEstimated0.35B params
Run with ToolPiper

General · Liquid AI · 2025-09-03

Q8_0Excellent
0.9 GB6% of RAM~229 tok/sEstimated0.35B params
Run with ToolPiper

General · Liquid AI · 2025-09-03

Q8_0Excellent
1.8 GB11% of RAM~68 tok/sEstimated1.17B params
Run with ToolPiper

General · Liquid AI · 2026-01-05

Q8_0Excellent
3.4 GB21% of RAM~31 tok/sEstimated2.57B params
Run with ToolPiper

General · weiboai · 2026-06-12

Q8_0Excellent
3.9 GB25% of RAM~26 tok/sEstimated3.09B params
Run with ToolPiper

General · ibm-granite · 2025-04-30

Q8_0Excellent
7.9 GB50% of RAMBenchmark needed6.67B params
Run with ToolPiper

General · Liquid AI · 2025-07-10

Q8_0Excellent
1.8 GB11% of RAM~68 tok/sEstimated1.17B params
Run with ToolPiper

General · stefanruseti · 2025-06-04

Q8_0Excellent
1.9 GB12% of RAM~65 tok/sEstimated1.24B params
Run with ToolPiper

General · ma7ee7 · 2026-07-30

Q8_0Excellent
4.0 GB25% of RAM~26 tok/sEstimated3.13B params
Run with ToolPiper

General · bytedance · 2025-10-28

Q8_0Excellent
2.1 GB13% of RAM~56 tok/sEstimated1.43B params
Run with ToolPiper

General · ibm-granite · 2025-10-07

Q8_0Excellent
0.9 GB6% of RAM~229 tok/sEstimated0.35B params
Run with ToolPiper

Multimodal · Liquid AI · 2025-08-12

Q8_0Excellent
2.3 GB14% of RAM~51 tok/sEstimated1.58B params
Run with ToolPiper

General · lgai-exaone · 2025-07-11

Q8_0Excellent
1.9 GB12% of RAM~63 tok/sEstimated1.28B params
Run with ToolPiper

General · Liquid AI · 2025-07-10

Q8_0Excellent
0.9 GB6% of RAM~229 tok/sEstimated0.35B params
Run with ToolPiper

General · Liquid AI · 2025-07-10

Q8_0Excellent
1.3 GB8% of RAM~108 tok/sEstimated0.74B params
Run with ToolPiper

General · Liquid AI · 2025-12-25

Q8_0Excellent
3.4 GB21% of RAM~31 tok/sEstimated2.57B params
Run with ToolPiper

General · NCAI · 2025-12-29

Q8_0Excellent
8.6 GB54% of RAMBenchmark needed7.25B params
Run with ToolPiper

Multimodal · ibm-granite · 2026-04-16

Q8_0Excellent
5.0 GB31% of RAM~20 tok/sEstimated4B params
Run with ToolPiper

General · Alibaba · 2025-09-23

Q8_0Excellent
1.3 GB8% of RAM~107 tok/sEstimated0.75B params
Run with ToolPiper

General · openonerec · 2025-12-30

Q8_0Excellent
2.9 GB18% of RAM~38 tok/sEstimated2.13B params
Run with ToolPiper

General · amd · 2025-05-17

Q8_0Excellent
2.2 GB14% of RAM~53 tok/sEstimated1.5B params
Run with ToolPiper

General · pfnet · 2025-02-05

Q8_0Excellent
1.9 GB12% of RAM~62 tok/sEstimated1.29B params
Run with ToolPiper

General · sapientinc · 2026-05-17

Q8_0Excellent
1.8 GB11% of RAM~68 tok/sEstimated1.18B params
Run with ToolPiper

Multimodal · Liquid AI · 2025-10-22

Q8_0Excellent
3.8 GB24% of RAM~27 tok/sEstimated3B params
Run with ToolPiper

General · Liquid AI · 2025-09-22

Q8_0Excellent
3.4 GB21% of RAM~31 tok/sEstimated2.57B params
Run with ToolPiper

General · viorikaai-org · 2026-07-05

Q8_0Excellent
0.6 GB3% of RAM~1,603 tok/sEstimated0.05B params
Run with ToolPiper

General · bananamind · 2026-07-17

Q8_0Excellent
0.5 GB3% of RAM~8,014 tok/sEstimated0.01B params
Run with ToolPiper

General · maliosdark · 2026-07-09

Q8_0Excellent
0.6 GB3% of RAM~1,603 tok/sEstimated0.05B params
Run with ToolPiper

General · raidium · 2026-06-15

Q8_0Excellent
0.5 GB3% of RAM~4,007 tok/sEstimated0.02B params
Run with ToolPiper

Multimodal · NCAI · 2025-12-29

Q8_0Excellent
9.0 GB56% of RAMBenchmark needed7.58B params
Run with ToolPiper

Embedding · taide · 2026-06-12

Q8_0Excellent
0.8 GB5% of RAM~267 tok/sEstimated0.3B params
Run with ToolPiper

General · Alibaba · 2025-04-27

Q8_0Excellent
1.3 GB8% of RAM~107 tok/sEstimated0.75B params
Run with ToolPiper

Multimodal · zai-org

Q8_0Excellent
2.0 GB12% of RAM~60 tok/sEstimated1.33B params
Run with ToolPiper

Multimodal · datalab-to

Q8_0Excellent
1.3 GB8% of RAM~116 tok/sEstimated0.69B params
Run with ToolPiper

Multimodal · openbmb

Q8_0Excellent
2.0 GB12% of RAM~62 tok/sEstimated1.3B params
Run with ToolPiper

General · Alibaba · 2025-04-28

Q8_0Excellent
1.2 GB7% of RAM~134 tok/sEstimated0.6B params
Run with ToolPiper

Reasoning · DeepSeek · 2025-01-20

Q8_0Excellent
2.5 GB16% of RAM~45 tok/sEstimated1.78B params
Run with ToolPiper

Multimodal · tencent

Q8_0Excellent
1.7 GB11% of RAMBenchmark needed1.12B params
Run with ToolPiper

General · distil-labs

Q8_0Excellent
0.9 GB6% of RAM~229 tok/sEstimated0.35B params
Run with ToolPiper

General · farbodtavakkoli

Q8_0Excellent
1.8 GB12% of RAM~66 tok/sEstimated1.21B params
Run with ToolPiper

Multimodal · ath-maas

Q8_0Excellent
1.4 GB9% of RAM~94 tok/sEstimated0.85B params
Run with ToolPiper

Multimodal · Liquid AI

Q8_0Excellent
1.0 GB6% of RAM~178 tok/sEstimated0.45B params
Run with ToolPiper

Multimodal · paddlepaddle

Q8_0Excellent
1.6 GB10% of RAM~83 tok/sEstimated0.96B params
Run with ToolPiper

General · Liquid AI

Q8_0Excellent
0.9 GB6% of RAM~229 tok/sEstimated0.35B params
Run with ToolPiper

Chat · uzlm · 2025-09-03

Q8_0Excellent
1.9 GB12% of RAM~65 tok/sEstimated1.24B params
Run with ToolPiper

General · Liquid AI · 2025-10-07

Q8_0Excellent
9.8 GB61% of RAMBenchmark needed8.34B params
Run with ToolPiper

Multimodal · paddlepaddle

Q8_0Excellent
1.6 GB10% of RAM~83 tok/sEstimated0.96B params
Run with ToolPiper

General · ai21labs · 2026-01-06

Q8_0Excellent
3.9 GB24% of RAMBenchmark needed3.03B params
Run with ToolPiper

General · adamlucek

Q8_0Excellent
1.9 GB12% of RAM~65 tok/sEstimated1.24B params
Run with ToolPiper

Coding · shahriarferdoush

Q8_0Excellent
1.9 GB12% of RAM~65 tok/sEstimated1.24B params
Run with ToolPiper

General · ahczhg

Q8_0Excellent
1.9 GB12% of RAM~65 tok/sEstimated1.24B params
Run with ToolPiper

General · onnx-community · 2025-04-28

Q8_0Excellent
1.0 GB6% of RAM~178 tok/sEstimated0.45B params
Run with ToolPiper

General · etherll

Q8_0Excellent
1.3 GB8% of RAM~108 tok/sEstimated0.74B params
Run with ToolPiper

General · baidu

Q8_0Excellent
0.9 GB6% of RAM~223 tok/sEstimated0.36B params
Run with ToolPiper

General · Liquid AI

Q8_0Excellent
1.8 GB11% of RAM~68 tok/sEstimated1.17B params
Run with ToolPiper

General · openbmb

Q8_0Excellent
1.7 GB11% of RAM~74 tok/sEstimated1.08B params
Run with ToolPiper

General · benjamin

Q8_0Excellent
1.7 GB11% of RAM~75 tok/sEstimated1.07B params
Run with ToolPiper

General · lemonelabs

Q8_0Excellent
1.8 GB12% of RAM~66 tok/sEstimated1.21B params
Run with ToolPiper

General · openbmb · 2025-06-05

Q8_0Excellent
1.0 GB6% of RAM~186 tok/sEstimated0.43B params
Run with ToolPiper

General · farbodtavakkoli

Q8_0Excellent
2.5 GB15% of RAMBenchmark needed1.77B params
Run with ToolPiper

General · novachronoai

Q8_0Excellent
1.8 GB12% of RAM~66 tok/sEstimated1.21B params
Run with ToolPiper

Multimodal · paddlepaddle

Q8_0Excellent
1.6 GB10% of RAM~83 tok/sEstimated0.96B params
Run with ToolPiper

General · kamilamila

Q8_0Excellent
1.2 GB7% of RAM~129 tok/sEstimated0.62B params
Run with ToolPiper

General · arcee-ai

Q8_0Excellent
7.3 GB46% of RAMBenchmark needed6.12B params
Run with ToolPiper

General · Liquid AI

Q8_0Excellent
1.8 GB12% of RAM~66 tok/sEstimated1.21B params
Run with ToolPiper
Q8_0Excellent
1.7 GB11% of RAM~74 tok/sEstimated1.08B params
Run with ToolPiper

General · ordenwills

Q8_0Excellent
0.9 GB6% of RAM~229 tok/sEstimated0.35B params
Run with ToolPiper
Q8_0Excellent
2.1 GB13% of RAM~58 tok/sEstimated1.39B params
Run with ToolPiper

General · carsenk

Q8_0Excellent
1.9 GB12% of RAM~65 tok/sEstimated1.24B params
Run with ToolPiper

Reasoning · nvidia

Q8_0Excellent
2.2 GB14% of RAM~52 tok/sEstimated1.54B params
Run with ToolPiper

General · openbmb

Q8_0Excellent
2.0 GB12% of RAM~62 tok/sEstimated1.3B params
Run with ToolPiper

General · ibm-granite

Q8_0Excellent
2.1 GB13% of RAM~55 tok/sEstimated1.46B params
Run with ToolPiper

General · pyoakum

Q8_0Excellent
6.5 GB40% of RAMBenchmark needed5.35B params
Run with ToolPiper

General · ibm-granite

Q8_0Excellent
4.2 GB26% of RAMBenchmark needed3.3B params
Run with ToolPiper
Q8_0Excellent
2.0 GB12% of RAM~62 tok/sEstimated1.3B params
Run with ToolPiper

General · skis-ai-research

Q8_0Excellent
1.8 GB11% of RAM~68 tok/sEstimated1.17B params
Run with ToolPiper

General · thkim0305

Q8_0Excellent
1.6 GB10% of RAM~80 tok/sEstimated1B params
Run with ToolPiper
Q8_0Excellent
1.5 GB9% of RAM~92 tok/sEstimated0.87B params
Run with ToolPiper

Coding · rahul7star

Q8_0Excellent
1.5 GB9% of RAM~92 tok/sEstimated0.87B params
Run with ToolPiper

General · fableforge-ai · 2026-07-05

Q8_0Excellent
2.2 GB14% of RAM~52 tok/sEstimated1.54B params
Run with ToolPiper
Q8_0Excellent
6.9 GB43% of RAMBenchmark needed5.75B params
Run with ToolPiper

General · artificialguybr

Q8_0Excellent
1.9 GB12% of RAM~65 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 GB7% of RAM~148 tok/sEstimated0.54B params
Run with ToolPiper

General · primeintellect

Q8_0Excellent
1.1 GB7% of RAMBenchmark needed0.54B params
Run with ToolPiper

General · reaperdoesntknow

Q8_0Excellent
1.6 GB10% of RAM~79 tok/sEstimated1.01B params
Run with ToolPiper

General · darthcrawl · 2026-05-07

Q8_0Excellent
0.5 GB3% of RAM~2,004 tok/sEstimated0.04B params
Run with ToolPiper

General · appvoid

Q8_0Excellent
0.6 GB4% of RAM~890 tok/sEstimated0.09B params
Run with ToolPiper

General · pinkstack

Q8_0Excellent
0.9 GB6% of RAM~229 tok/sEstimated0.35B params
Run with ToolPiper

Coding · Liquid AI

Q8_0Excellent
0.9 GB6% of RAM~229 tok/sEstimated0.35B params
Run with ToolPiper

General · squ11z1

Q8_0Excellent
0.9 GB6% of RAM~229 tok/sEstimated0.35B params
Run with ToolPiper

General · iselabvn

Q8_0Excellent
0.9 GB6% of RAM~229 tok/sEstimated0.35B params
Run with ToolPiper

General · meddies

Q8_0Excellent
0.9 GB6% of RAM~229 tok/sEstimated0.35B params
Run with ToolPiper

General · mihaipopa-1

Q8_0Excellent
0.9 GB6% of RAM~229 tok/sEstimated0.35B params
Run with ToolPiper

General · lazos

Q8_0Excellent
0.9 GB6% of RAM~229 tok/sEstimated0.35B params
Run with ToolPiper

General · q1ngmang

Q8_0Excellent
0.9 GB6% of RAM~229 tok/sEstimated0.35B params
Run with ToolPiper

General · baidu

Q8_0Excellent
0.9 GB6% of RAM~223 tok/sEstimated0.36B params
Run with ToolPiper

Multimodal · Liquid AI

Q8_0Excellent
1.0 GB6% of RAM~178 tok/sEstimated0.45B params
Run with ToolPiper
Q8_0Excellent
1.2 GB7% of RAM~129 tok/sEstimated0.62B params
Run with ToolPiper

General · melikegks

Q8_0Excellent
1.3 GB8% of RAM~107 tok/sEstimated0.75B params
Run with ToolPiper
Q8_0Excellent
1.3 GB8% of RAM~107 tok/sEstimated0.75B params
Run with ToolPiper

Reasoning · supralabs

Q8_0Excellent
1.3 GB8% of RAM~107 tok/sEstimated0.75B params
Run with ToolPiper

General · iselabvn

Q8_0Excellent
1.3 GB8% of RAM~107 tok/sEstimated0.75B params
Run with ToolPiper

Multimodal · 8f-ai

Q8_0Excellent
1.3 GB8% of RAM~107 tok/sEstimated0.75B params
Run with ToolPiper

General · kylesayrs

Q8_0Excellent
1.4 GB9% of RAMBenchmark needed0.8B params
Run with ToolPiper

General · inference-optimization

Q8_0Excellent
1.4 GB9% of RAMBenchmark needed0.85B params
Run with ToolPiper

General · cooperdk

Q8_0Excellent
1.4 GB9% of RAM~94 tok/sEstimated0.85B params
Run with ToolPiper

Multimodal · dingdust

Q8_0Excellent
1.4 GB9% of RAM~94 tok/sEstimated0.85B params
Run with ToolPiper

Multimodal · yuandaxia

Q8_0Excellent
1.4 GB9% of RAM~94 tok/sEstimated0.85B params
Run with ToolPiper

General · dingdust

Q8_0Excellent
1.7 GB11% of RAM~74 tok/sEstimated1.08B params
Run with ToolPiper

General · ermiaazarkhalili

Q8_0Excellent
1.7 GB11% of RAM~74 tok/sEstimated1.08B params
Run with ToolPiper

General · thepradip

Q8_0Excellent
1.7 GB11% of RAM~74 tok/sEstimated1.08B params
Run with ToolPiper

General · marinarosa

Q8_0Excellent
1.7 GB11% of RAM~74 tok/sEstimated1.08B params
Run with ToolPiper

General · marinarosa

Q8_0Excellent
1.7 GB11% of RAM~74 tok/sEstimated1.08B params
Run with ToolPiper

General · ephemeralyou

Q8_0Excellent
1.7 GB11% of RAM~74 tok/sEstimated1.08B params
Run with ToolPiper

General · marinarosa

Q8_0Excellent
1.7 GB11% of RAM~74 tok/sEstimated1.08B params
Run with ToolPiper

General · marinarosa

Q8_0Excellent
1.7 GB11% of RAM~74 tok/sEstimated1.08B params
Run with ToolPiper

General · ewinregirgojr

Q8_0Excellent
1.7 GB11% of RAM~74 tok/sEstimated1.08B params
Run with ToolPiper

Reasoning · healshsj

Q8_0Excellent
1.7 GB11% of RAM~74 tok/sEstimated1.08B params
Run with ToolPiper

Measured on the M6

Nobody has submitted a benchmark on the M6 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.

Where to go from here

What each step actually changes for local models, rather than which one is newer.

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 M6's 170 GB/s bus is shared by CPU, GPU, and Neural Engine, so a 32 GB machine can hand almost all of that to a model with no copy across a bus.

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. 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 M6 Mac mini run a 70B model?

No. A 70B model at Q4_K_M needs about 46 GB, and the largest M6 Mac mini tops out at 32 GB, which leaves about 28 GB for weights. The practical ceiling on this machine is around 42B parameters at Q4.

How much unified memory should I get with the M6 Mac mini?

Memory is the only spec that changes what you can run at all. 16 GB holds about a 20B model at Q4; 32 GB holds about 42B. 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 M6?

Token generation is bandwidth-bound, so M6 throughput scales with its 170 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 M6 lands in the tens of tokens per second and a 70B model lands in the single digits.

Should I buy the M6 Mac mini 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 M6 already holds about a 42B model at Q4. If your target model fits in 32 GB, waiting buys throughput rather than capability.

Run these models on your Mac mini

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