The M2 Max Mac Studio 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 56% of the Apple Silicon chips shipped in a Mac, against a 819 GB/s peak.
Its memory ceiling is above 61% 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.
3,388 of 3,641 models fit, and 3,127 of them run with headroom rather than as a squeeze.
3,541 of 3,641 models fit, and 3,385 of them run with headroom rather than as a squeeze.
3,556 of 3,641 models fit, and 3,503 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 3641 of 3641 models
Multimodal · Alibaba · 2026-02-28
Multimodal · Alibaba · 2026-02-28
Multimodal · Alibaba · 2026-02-28
Multimodal · Alibaba · 2026-02-28
Multimodal · Alibaba · 2026-02-27
Multimodal · Alibaba · 2026-02-27
General · Liquid AI · 2025-11-28
General · Liquid AI · 2025-11-28
Reasoning · Liquid AI · 2025-11-28
General · Liquid AI · 2025-11-28
General · Liquid AI · 2025-11-28
General · Liquid AI · 2025-11-28
General · Liquid AI · 2025-11-28
General · Liquid AI · 2025-11-28
General · Liquid AI · 2025-11-28
General · Liquid AI · 2025-11-28
General · Liquid AI · 2025-11-28
General · Liquid AI · 2025-11-28
General · Liquid AI · 2025-11-28
General · Liquid AI · 2025-11-28
General · Liquid AI · 2025-11-28
Reasoning · Liquid AI · 2025-11-28
General · ibm-granite · 2025-09-16
Chat · Liquid AI · 2025-11-28
Chat · Liquid AI · 2025-11-28
General · ibm-granite · 2025-09-16
Reasoning · jackrong · 2026-03-16
Chat · Liquid AI · 2025-11-28
General · NCAI · 2025-12-29
Reasoning · HuggingFace · 2025-07-08
General · Liquid AI · 2025-11-28
General · Liquid AI · 2025-11-28
Multimodal · NCAI · 2025-12-29
Multimodal · Alibaba · 2026-02-27
Multimodal · Google · 2025-07-30
Multimodal · Google · 2025-06-25
Multimodal · Liquid AI · 2025-11-28
Multimodal · Liquid AI · 2025-11-28
Multimodal · Liquid AI · 2025-11-28
Multimodal · Liquid AI · 2025-11-28
General · lgai-exaone · 2025-03-12
Multimodal · google · 2026-05
Multimodal · Alibaba · 2026-02-26
General · LG AI · 2025-07-15
General · raidium · 2026-06-15
Embedding · taide · 2026-06-12
General · Alibaba · 2025-04-27
General · Alibaba · 2025-04-27
Multimodal · Google · 2025-07-30
General · Alibaba · 2025-04-27
Multimodal · zai-org
Multimodal · Alibaba
Multimodal · Microsoft
General · Alibaba
General · Alibaba
Multimodal · openbmb
Reasoning · DeepSeek
Multimodal · rednote-hilab
Multimodal · datalab-to
General · ibm-granite
General · openbmb
Multimodal · rednote-hilab
General · hmellor
General · distil-labs
Multimodal · nanonets
General · farbodtavakkoli
General · Liquid AI
General · nanonets
Multimodal · ibm-granite
General · ibm-granite
General · Google
Multimodal · lkhl
Multimodal · typhoon-ai
General · jinaai
General · Alibaba
General · kristaller486
Reasoning · typhoon-ai
General · Upstage
General · zstanjj
General · ibm-granite
General · nvidia
General · weiboai
General · x-izhang
General · openai
General · paddlepaddle
General · twinkle-ai
General · Liquid AI
General · pfnet
General · openbmb
General · ibm-granite
General · baidu
General · jetbrains
General · amd
General · bytedance-seed
General · arcee-ai
General · adamlucek
Coding · shahriarferdoush
General · ahczhg
General · abaryan
General · etherll
General · stanford-oval
General · jetbrains
General · flowaicom
General · bllossom
General · farbodtavakkoli
General · z-lab
Reasoning · khazarai
General · kamilamila
General · radheneev
General · getonit
General · paddlepaddle
General · agentica-org
General · NousResearch
Reasoning · nvidia
General · inference-net
General · novaciano
General · dmusingu
Reasoning · nvidia
General · kgrabko
General · ordenwills
General · smcleish
General · carsenk
General · ibm-granite
Coding · ibm-granite
Reasoning · iffyuan
Reasoning · nvidia
General · zero-point-ai
General · stanfordaimi
General · Microsoft
General · dealignai
General · huihui-ai
General · ibm-granite
General · openbmb
General · ibm-granite
General · osaurusai
General · pyoakum
General · ibm-granite
General · anakin87
General · redix
General · treadon
General · tencent
General · thkim0305
General · skis-ai-research
General · menlo
General · staedi
General · thkim0305
General · magistrtheone
General · TII
Reasoning · jackrong
General · huihui-ai
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.
Mac Studio M2 Ultra
2x the memory bandwidth, up to 192 GB instead of 96 GB
Newer generationMac Studio M4 Max
1.4x the memory bandwidth, up to 128 GB instead of 96 GB
Used market alternativeMac Studio M1 Max
64 GB ceiling instead of 96 GB
Same chip, other MacMacBook Pro 14" M2 Max
The same chip in a different Mac
Same chip, other MacMacBook Pro 16" M2 Max
The same chip in a different Mac
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 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 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.