The M2 Mac mini runs local models at 100 GB/s of memory bandwidth with 8 to 24 GB of unified memory. On Apple Silicon that memory is shared with the GPU, so the whole pool is available for weights: at 24 GB you can hold roughly a 31B 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.
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.
Memory bandwidth is faster than 5% of the Apple Silicon chips shipped in a Mac, against a 1228 GB/s peak.
Its memory ceiling is above 5% of them, against a 512 GB peak.
Every option Apple sells with this chip. The model list below recomputes against the one you pick.
Unified memory
Unified memory is the ceiling and it is soldered, so this is the decision you cannot revisit.
4,997 of 6,563 models fit, and 3,331 of them run with headroom rather than as a squeeze.
5,572 of 6,563 models fit, and 5,054 of them run with headroom rather than as a squeeze.
6,032 of 6,563 models fit, and 5,271 of them run with headroom rather than as a squeeze.
Every model in the database against this exact configuration, at 100 GB/s. Ratings and speeds are the same numbers the model pages show.
Showing 6563 of 6563 models
General · Liquid AI · 2026-06-24
General · openbmb · 2026-05-21
General · ktruestory · 2026-05-28
Multimodal · Alibaba · 2026-02-28
Multimodal · Alibaba · 2026-02-28
General · Liquid AI · 2026-03-31
General · cagrigungor · 2026-08-06
General · petrouil · 2026-07-23
Reasoning · openonerec · 2026-06-09
Multimodal · Liquid AI · 2026-01-05
General · Liquid AI · 2025-10-28
General · Liquid AI · 2026-01-20
General · Liquid AI · 2026-01-05
General · Liquid AI · 2026-01-04
General · frontiersmind · 2026-08-03
Multimodal · Liquid AI · 2025-08-12
General · Liquid AI · 2025-09-30
General · Liquid AI · 2025-09-03
General · Liquid AI · 2025-08-25
General · Liquid AI · 2025-09-03
Chat · Liquid AI · 2026-01-06
General · Liquid AI · 2025-07-10
General · Liquid AI · 2025-07-10
General · Liquid AI · 2025-08-22
General · Liquid AI · 2025-09-03
General · Liquid AI · 2025-09-03
Multimodal · Alibaba · 2026-02-28
Multimodal · Alibaba · 2026-02-28
General · hmellor · 2025-07-22
General · Alibaba · 2025-09-23
General · Liquid AI · 2025-07-10
General · bytedance · 2025-10-28
General · ibm-granite · 2025-10-07
Multimodal · Liquid AI · 2025-08-12
General · lgai-exaone · 2025-07-11
General · viorikaai-org · 2026-07-05
General · bananamind · 2026-07-17
General · maliosdark · 2026-07-09
General · raidium · 2026-06-15
Embedding · taide · 2026-06-12
General · Alibaba · 2025-04-27
General · radixark · 2026-07-27
Multimodal · datalab-to
General · Alibaba · 2025-04-28
General · distil-labs
Multimodal · ath-maas
Multimodal · Liquid AI
Multimodal · paddlepaddle
General · amd · 2025-05-17
General · stefanruseti · 2025-06-04
General · Liquid AI
Multimodal · paddlepaddle
General · onnx-community · 2025-04-28
General · etherll
General · baidu
General · openbmb · 2025-06-05
General · farbodtavakkoli
Multimodal · paddlepaddle
General · kamilamila
General · ordenwills
Reasoning · jackrong
Coding · rahul7star
General · Microsoft
General · Microsoft
General · tencent
General · primeintellect
General · goekdeniz-guelmez · 2026-07-31
General · darthcrawl · 2026-05-07
General · appvoid
General · pinkstack
Coding · Liquid AI
General · squ11z1
General · iselabvn
General · meddies
General · mihaipopa-1
General · lazos
General · q1ngmang
General · baidu
Multimodal · Liquid AI
General · TII
General · melikegks
Coding · dalatexcoder
Reasoning · supralabs
General · iselabvn
Multimodal · 8f-ai
General · kylesayrs
General · inference-optimization
General · cooperdk
Multimodal · dingdust
Multimodal · yuandaxia
Reasoning · healshsj
Multimodal · zai-org
General · Alibaba · 2024-05-31
Multimodal · openbmb
Reasoning · DeepSeek · 2025-01-20
Multimodal · tencent
General · farbodtavakkoli
General · Google · 2022-03-02
General · pfnet · 2025-02-05
Chat · uzlm · 2025-09-03
General · sapientinc · 2026-05-17
General · adamlucek
Coding · shahriarferdoush
General · ahczhg
General · Liquid AI
General · openbmb
General · benjamin
General · lemonelabs
General · novachronoai
General · Liquid AI
General · saidutta69
General · carsenk
Reasoning · nvidia
General · bezzam
General · ibm-granite
General · skis-ai-research
General · thkim0305
General · fableforge-ai · 2026-07-05
General · artificialguybr
General · reaperdoesntknow
General · limloop
General · dingdust
General · ermiaazarkhalili
General · thepradip
General · marinarosa
General · marinarosa
General · ephemeralyou
General · marinarosa
General · marinarosa
General · ewinregirgojr
General · andrew0425
General · daremodels
General · ermiaazarkhalili
General · saidutta69
Multimodal · inclusionai
General · yasserrmd
General · davidau
General · davidau
General · davidau
General · davidau
General · marcodsn
General · orionllm
General · ali-thowfeek
General · roky-dev
General · novacorp
Multimodal · Liquid AI
General · Microsoft
Multimodal · opengvlab
General · Microsoft
General · farbodtavakkoli
Nobody has submitted a benchmark on the M2 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 each step actually changes for local models, rather than which one is newer.
Mac mini M2 Pro
2x the memory bandwidth, up to 32 GB instead of 24 GB
Newer generationMac mini M6
1.7x the memory bandwidth, up to 32 GB instead of 24 GB
Used market alternativeMac mini M1
32% less memory bandwidth, 16 GB ceiling instead of 24 GB
Same chip, other MacMacBook Air M2
The same chip in a different Mac
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.
Projected chip · expected 2027
240 GB/s · 16 to 48 GB unified memory
12-core CPU · 12 or 16-core GPU · 76 TOPS Neural Engine
Would hold about a 63B model at Q4
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 M2's 100 GB/s bus is shared by CPU, GPU, and Neural Engine, so a 24 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 M2 at 24 GB still gives you 100 GB/s and a hard 31B ceiling, and neither number degrades with age the way a battery does.
No. A 70B model at Q4_K_M needs about 46 GB, and the largest M2 Mac mini tops out at 24 GB, which leaves about 21 GB for weights. The practical ceiling on this machine is around 31B parameters at Q4.
Memory is the only spec that changes what you can run at all. 8 GB holds about a 9B model at Q4; 24 GB holds about 31B. It is soldered, so this is a one-time decision, and it is the upgrade worth paying for before core count.
Token generation is bandwidth-bound, so M2 throughput scales with its 100 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 M2 lands in the tens of tokens per second and a 70B model lands in the single digits.
For inference, the specs that matter do not age: 100 GB/s and up to 24 GB of unified memory are the same numbers today as they were in 2022. A used M2 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.
ToolPiper downloads, manages, and runs local models on Apple Silicon. Free, and nothing leaves the machine.