The M4 Max Mac Studio runs local models at 410 to 546 GB/s of memory bandwidth with 36 to 128 GB of unified memory. On Apple Silicon that memory is shared with the GPU, so the whole pool is available for weights: at 128 GB you can hold roughly a 172B dense model at Q4. The Max is where the bus gets wide enough that model size, not bandwidth, becomes the thing you plan around.
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 70% of the Apple Silicon chips shipped in a Mac, against a 1228 GB/s peak.
Its memory ceiling is above 65% of them, against a 512 GB peak.
Every option Apple sells with this chip. The model list below recomputes against the one you pick.
GPU cores
Unified memory
Apple couples memory to the core count on this chip, so the options change with the bin above.
Unified memory is the ceiling and it is soldered, so this is the decision you cannot revisit.
6,120 of 6,563 models fit, and 5,827 of them run with headroom rather than as a squeeze.
6,273 of 6,563 models fit, and 6,033 of them run with headroom rather than as a squeeze.
6,357 of 6,563 models fit, and 6,086 of them run with headroom rather than as a squeeze.
6,420 of 6,563 models fit, and 6,334 of them run with headroom rather than as a squeeze.
Every model in the database against this exact configuration, at 410 GB/s. Ratings and speeds are the same numbers the model pages show.
Showing 6563 of 6563 models
General · radixark · 2026-07-27
General · openbmb · 2026-05-21
General · farbodtavakkoli · 2026-06-17
General · Liquid AI · 2026-05-28
General · weiboai · 2026-06-12
General · Liquid AI · 2026-07-28
General · Liquid AI · 2026-06-24
General · ma7ee7 · 2026-07-30
General · goekdeniz-guelmez · 2026-07-31
General · ktruestory · 2026-05-28
General · petrouil · 2026-07-23
General · ibm-granite · 2026-04-06
General · internscience · 2026-07-13
General · nanbeige · 2026-07-21
Multimodal · Alibaba · 2026-02-28
Multimodal · Alibaba · 2026-02-28
Multimodal · Alibaba · 2026-02-28
Multimodal · Alibaba · 2026-02-28
Multimodal · ibm-granite · 2026-04-16
General · Liquid AI · 2026-03-31
General · nvidia · 2026-03-02
General · cagrigungor · 2026-08-06
Multimodal · Alibaba · 2026-02-27
Multimodal · Google · 2026-03-02
Multimodal · Alibaba · 2026-02-27
Multimodal · Liquid AI · 2026-01-05
General · lukebailey181pub · 2026-04-21
General · Liquid AI · 2026-01-20
General · ai21labs · 2026-01-06
Reasoning · openonerec · 2026-06-09
General · Liquid AI · 2026-01-05
General · Liquid AI · 2026-01-04
General · Liquid AI · 2025-12-25
General · Liquid AI · 2026-01-05
Multimodal · davidau · 2026-02-02
General · inclusionai · 2026-02-09
General · Liquid AI · 2025-10-28
Multimodal · Liquid AI · 2025-10-22
General · frontiersmind · 2026-08-03
Multimodal · Google · 2026-03-02
General · deepreinforce-ai · 2026-06-21
Chat · Liquid AI · 2026-01-06
General · typhoon-ai · 2025-09-23
General · ibm-granite · 2025-09-16
General · ibm-granite · 2025-09-16
Multimodal · Liquid AI · 2025-08-12
General · ravichandranj · 2026-02-13
General · openonerec · 2025-12-30
General · ibm-granite · 2025-09-16
General · bytedance · 2025-10-28
General · Liquid AI · 2025-10-07
General · z-lab · 2026-01-04
Multimodal · Liquid AI · 2025-08-12
General · Liquid AI · 2025-09-22
General · Liquid AI · 2025-09-30
General · Liquid AI · 2025-08-22
Reasoning · jackrong · 2026-03-16
General · Liquid AI · 2025-09-03
General · Liquid AI · 2025-09-03
General · Liquid AI · 2025-08-25
General · Liquid AI · 2025-09-03
General · Liquid AI · 2025-09-03
General · NCAI · 2025-12-29
General · Alibaba · 2025-08-05
General · hmellor · 2025-07-22
General · inclusionai · 2025-11-25
General · ibm-granite · 2025-04-30
General · Liquid AI · 2025-07-10
General · amd · 2025-05-17
General · stefanruseti · 2025-06-04
General · obliteratus · 2026-04-15
General · lgai-exaone · 2025-07-11
General · Liquid AI · 2025-07-10
General · menlo · 2025-06-25
General · Liquid AI · 2025-07-10
Multimodal · NCAI · 2025-12-29
Multimodal · Alibaba · 2026-02-27
General · huggingfacetb · 2025-07-08
Multimodal · Alibaba · 2026-02-26
General · huggingfacetb · 2025-06-19
General · Alibaba · 2025-09-23
Reasoning · Microsoft · 2025-04-29
General · ibm-granite · 2026-04-16
General · allenai · 2025-11-18
General · pfnet · 2025-02-05
General · bytedance-seed · 2025-04-09
Chat · baseten · 2025-09-12
General · allenai · 2026-01-28
General · sapientinc · 2026-05-17
General · ibm-granite · 2025-10-07
General · fableforge-ai · 2026-07-05
General · viorikaai-org · 2026-07-05
General · bananamind · 2026-07-17
General · lgai-exaone · 2025-03-12
General · maliosdark · 2026-07-09
General · raidium · 2026-06-15
General · shaungves · 2026-06-19
General · preparebuddy · 2026-06-02
Embedding · taide · 2026-06-12
General · Alibaba · 2025-04-27
General · Alibaba · 2025-04-27
Multimodal · Alibaba · 2025-01-26
General · ibm-granite · 2026-04-06
Multimodal · zai-org
Multimodal · google · 2026-05
Multimodal · Alibaba
Reasoning · DeepSeek · 2025-05-29
Multimodal · datalab-to
Multimodal · Microsoft
General · Alibaba · 2025-04-28
Multimodal · openbmb
General · Alibaba · 2025-04-28
Multimodal · nanonets
Multimodal · rednote-hilab
Reasoning · DeepSeek · 2025-01-20
General · Alibaba · 2025-09-23
Multimodal · moonshotai
Multimodal · typhoon-ai
Multimodal · tencent
Multimodal · dots-studio
General · distil-labs
General · farbodtavakkoli
General · nvidia · 2026-03-18
Multimodal · raxcore-dev
Multimodal · moonshotai
General · jinaai
General · allenai · 2025-09-12
Multimodal · ath-maas
General · anton-hugging · 2026-02-06
General · kristaller486
Multimodal · Alibaba
Multimodal · Liquid AI
Reasoning · typhoon-ai
General · zstanjj
Multimodal · paddlepaddle
General · ibm-granite
General · x-izhang
Multimodal · nanonets
General · empero-ai · 2026-06-19
General · twinkle-ai
General · Liquid AI
Chat · uzlm · 2025-09-03
General · ibm-granite
Multimodal · paddlepaddle
General · jetbrains
Chat · pearl-ai · 2026-02-26
General · adamlucek
Coding · shahriarferdoush
General · ahczhg
General · onnx-community · 2025-04-28
Apple ties the memory bus to the bin on this chip: 410 GB/s at 32 cores and 546 GB/s at 40. That moves tokens per second. It does not move which models fit, because that is memory, not cores.
| Configuration | Memory bandwidth | Memory options | Models that fit |
|---|---|---|---|
| 14-core CPU, 32-core GPU | 410 GB/s | 36 GB | Identical |
| 16-core CPU, 40-core GPU | 546 GB/s | 48, 64, 128 GB | Identical |
On openbuddy zero 56b v21.2 32k the 32-core generates about 11 tok/s and the 40-core about 14 tok/s, a 33% difference. Both hold the model at the same quantization.
Nobody has submitted a benchmark on the M4 Max 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 Studio M5 Max
1.1x the memory bandwidth
Used market alternativeMac Studio M2 Max
27% less memory bandwidth, 96 GB ceiling instead of 128 GB
Same chip, other MacMacBook Pro 14" M4 Max
The same chip in a different Mac
Same chip, other MacMacBook Pro 16" M4 Max
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
1382 GB/s · 48 to 384 GB unified memory
20-core CPU · 56 or 64-core GPU · 76 TOPS Neural Engine
Would hold about a 521B 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 Max's 546 GB/s bus is shared by CPU, GPU, and Neural Engine, so a 128 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 Studio exists for this workload. It carries the widest memory buses and the highest capacities Apple sells, and it runs at full clocks indefinitely. A used M4 Max at 128 GB still gives you 546 GB/s and a hard 172B ceiling, and neither number degrades with age the way a battery does.
Yes, at 128 GB. A 70B model at Q4_K_M needs about 46 GB including an 8K context, and 128 GB of unified memory leaves about 112 GB for weights once macOS takes its share. At 36 GB it does not fit at any quantization worth running.
Memory is the only spec that changes what you can run at all. 36 GB holds about a 47B model at Q4; 128 GB holds about 172B. 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 Max throughput scales with its 546 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 Max lands in the tens of tokens per second and a 70B model lands in the single digits.
For throughput, yes: Apple ties bandwidth to the bin here, so the 32-core runs at 410 GB/s and the 40-core at 546 GB/s, about 33% more. For fit, no: both bins hold exactly the same models, because that is set by memory rather than by cores.
For inference, the specs that matter do not age: 546 GB/s and up to 128 GB of unified memory are the same numbers today as they were in 2024. A used M4 Max 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.