The M4 Mac mini runs local models at 120 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.
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 15% 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.
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.
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.
6,082 of 6,563 models fit, and 5,571 of them run with headroom rather than as a squeeze.
Every model in the database against this exact configuration, at 120 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 · ktruestory · 2026-05-28
General · openbmb · 2026-05-21
General · petrouil · 2026-07-23
Multimodal · Alibaba · 2026-02-28
Multimodal · Alibaba · 2026-02-28
General · Liquid AI · 2026-03-31
General · cagrigungor · 2026-08-06
General · Liquid AI · 2026-01-20
Reasoning · openonerec · 2026-06-09
General · radixark · 2026-07-27
Multimodal · Liquid AI · 2026-01-05
General · Liquid AI · 2025-10-28
General · Liquid AI · 2026-01-05
General · Liquid AI · 2026-01-04
General · goekdeniz-guelmez · 2026-07-31
General · frontiersmind · 2026-08-03
Multimodal · Alibaba · 2026-02-28
Multimodal · Alibaba · 2026-02-28
Chat · Liquid AI · 2026-01-06
General · ibm-granite · 2025-09-16
General · Liquid AI · 2026-05-28
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
General · farbodtavakkoli · 2026-06-17
General · hmellor · 2025-07-22
General · ibm-granite · 2025-04-30
General · Liquid AI · 2025-07-10
Multimodal · Liquid AI · 2025-08-12
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
General · Alibaba · 2025-09-23
General · stefanruseti · 2025-06-04
General · bytedance · 2025-10-28
General · ibm-granite · 2025-10-07
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
General · NCAI · 2025-12-29
Embedding · taide · 2026-06-12
General · Alibaba · 2025-04-27
Multimodal · datalab-to
General · Alibaba · 2025-04-28
Reasoning · DeepSeek · 2025-01-20
Multimodal · tencent
General · distil-labs
Multimodal · ath-maas
General · Liquid AI · 2026-07-28
Multimodal · Liquid AI
Multimodal · paddlepaddle
General · openonerec · 2025-12-30
General · amd · 2025-05-17
General · Liquid AI
General · pfnet · 2025-02-05
Chat · uzlm · 2025-09-03
Multimodal · paddlepaddle
General · sapientinc · 2026-05-17
Coding · shahriarferdoush
General · onnx-community · 2025-04-28
General · etherll
General · baidu
General · openbmb
General · benjamin
General · openbmb · 2025-06-05
General · farbodtavakkoli
Multimodal · paddlepaddle
General · kamilamila
General · arcee-ai
General · saidutta69
General · ordenwills
General · pyoakum
General · ibm-granite
General · thkim0305
Reasoning · jackrong
Coding · rahul7star
General · osaurusai
General · Microsoft
General · Microsoft
General · tencent
General · primeintellect
General · reaperdoesntknow
Multimodal · NCAI · 2025-12-29
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
General · dingdust
General · ermiaazarkhalili
General · thepradip
General · marinarosa
General · marinarosa
General · ephemeralyou
General · marinarosa
General · marinarosa
General · ewinregirgojr
Reasoning · healshsj
General · andrew0425
General · daremodels
General · ermiaazarkhalili
General · saidutta69
Multimodal · inclusionai
General · dealignai
Multimodal · zai-org
General · Alibaba · 2024-05-31
Multimodal · openbmb
General · farbodtavakkoli
Multimodal · ibm-granite · 2026-04-16
General · Google · 2022-03-02
Reasoning · typhoon-ai
General · Liquid AI · 2025-10-07
General · adamlucek
General · ahczhg
General · Liquid AI
Multimodal · lkhl
General · lemonelabs
General · novachronoai
General · Liquid AI
General · smcleish
General · carsenk
Reasoning · nvidia
General · bezzam
General · openbmb
General · ibm-granite
Nobody has submitted a benchmark on the M4 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 M4 Pro
2.3x the memory bandwidth, up to 64 GB instead of 32 GB
Newer generationMac mini M6
1.4x the memory bandwidth
Used market alternativeMac mini M2
17% less memory bandwidth, 24 GB ceiling instead of 32 GB
Same chip, other MacMacBook Air M4
The same chip in a different Mac
Same chip, other MacMacBook Pro 14" M4
The same chip in a different Mac
Same chip, other MaciMac M4
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 M4's 120 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.
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 at 32 GB still gives you 120 GB/s and a hard 42B 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 M4 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.
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.
Token generation is bandwidth-bound, so M4 throughput scales with its 120 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 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: 120 GB/s and up to 32 GB of unified memory are the same numbers today as they were in 2024. A used M4 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.