The M2 Max MacBook Pro 14" runs local models at 400 GB/s of memory bandwidth with 32 to 96 GB of unified memory. On Apple Silicon that memory is shared with the GPU, so the whole pool is available for weights: at 96 GB you can hold roughly a 129B 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 55% of the Apple Silicon chips shipped in a Mac, against a 1228 GB/s peak.
Its memory ceiling is above 60% 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
Unified memory is the ceiling and it is soldered, so this is the decision you cannot revisit.
6,082 of 6,563 models fit, and 5,571 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.
6,384 of 6,563 models fit, and 6,271 of them run with headroom rather than as a squeeze.
Every model in the database against this exact configuration, at 400 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 · 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 · Liquid AI · 2026-01-20
General · ai21labs · 2026-01-06
Reasoning · openonerec · 2026-06-09
General · Liquid AI · 2026-01-05
General · nvidia · 2026-03-02
General · Liquid AI · 2026-01-04
General · Liquid AI · 2025-12-25
General · Liquid AI · 2026-01-05
Multimodal · davidau · 2026-02-02
General · Liquid AI · 2025-10-28
General · lukebailey181pub · 2026-04-21
Multimodal · Liquid AI · 2025-10-22
General · frontiersmind · 2026-08-03
Multimodal · Google · 2026-03-02
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
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 · deepreinforce-ai · 2026-06-21
General · Alibaba · 2025-08-05
General · hmellor · 2025-07-22
General · ibm-granite · 2025-04-30
General · Liquid AI · 2025-07-10
General · inclusionai · 2026-02-09
General · amd · 2025-05-17
General · stefanruseti · 2025-06-04
General · z-lab · 2026-01-04
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 · inclusionai · 2025-11-25
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 · obliteratus · 2026-04-15
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 · preparebuddy · 2026-06-02
Embedding · taide · 2026-06-12
General · Alibaba · 2025-04-27
General · Alibaba · 2025-04-27
Multimodal · Alibaba · 2025-01-26
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 · typhoon-ai
Multimodal · tencent
Multimodal · dots-studio
General · distil-labs
General · farbodtavakkoli
General · nvidia · 2026-03-18
Multimodal · raxcore-dev
General · jinaai
General · allenai · 2025-09-12
Multimodal · ath-maas
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 · allenai · 2026-01-28
General · jetbrains
General · adamlucek
Coding · shahriarferdoush
General · ahczhg
General · onnx-community · 2025-04-28
General · etherll
Multimodal · vchitect
General · baidu
General · Liquid AI
Multimodal · idea-research
General · openbmb
Both bins run the same 400 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.
| Configuration | Memory bandwidth | Memory options | Models that fit |
|---|---|---|---|
| 12-core CPU, 30-core GPU | 400 GB/s | 32, 64, 96 GB | Identical |
| 12-core CPU, 38-core GPU | 400 GB/s | 32, 64, 96 GB | Identical |
Nobody has submitted a benchmark on the M2 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.
MacBook Pro 14" M5 Max
1.5x the memory bandwidth, up to 128 GB instead of 96 GB
Used market alternativeMacBook Pro 14" M1 Max
64 GB ceiling instead of 96 GB
Same chip, other MacMacBook Pro 16" M2 Max
The same chip in a different Mac
Same chip, other MacMac Studio M2 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 M2 Max's 400 GB/s bus is shared by CPU, GPU, and Neural Engine, so a 96 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 14-inch chassis cools well enough to hold its clocks through a long generation run, and it is the smallest machine Apple puts a Max chip in. A used M2 Max at 96 GB still gives you 400 GB/s and a hard 129B ceiling, and neither number degrades with age the way a battery does.
Yes, at 96 GB. A 70B model at Q4_K_M needs about 46 GB including an 8K context, and 96 GB of unified memory leaves about 84 GB for weights once macOS takes its share. At 32 GB it does not fit at any quantization worth running.
Memory is the only spec that changes what you can run at all. 32 GB holds about a 42B model at Q4; 96 GB holds about 129B. 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 Max throughput scales with its 400 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 Max lands in the tens of tokens per second and a 70B model lands in the single digits.
Not for LLMs. Both bins run the same 400 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.
For inference, the specs that matter do not age: 400 GB/s and up to 96 GB of unified memory are the same numbers today as they were in 2023. A used M2 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.