The M2 Pro MacBook Pro 16" runs local models at 200 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. The Pro roughly doubles the base chip's memory bus. That moves mid-size models from usable to comfortable without moving you into desktop money.
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 33% of the Apple Silicon chips shipped in a Mac, against a 819 GB/s peak.
Its memory ceiling is above 17% 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.
3,128 of 3,641 models fit, and 2,907 of them run with headroom rather than as a squeeze.
3,388 of 3,641 models fit, and 3,127 of them run with headroom rather than as a squeeze.
Every model in the database against this exact configuration, at 200 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
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
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 · Liquid AI · 2025-11-28
General · Liquid AI · 2025-11-28
General · Liquid AI · 2025-11-28
General · Liquid AI · 2025-11-28
General · NCAI · 2025-12-29
Multimodal · Alibaba · 2026-02-27
Reasoning · HuggingFace · 2025-07-08
Multimodal · Alibaba · 2026-02-27
Multimodal · Liquid AI · 2025-11-28
Multimodal · Liquid AI · 2025-11-28
General · Liquid AI · 2025-11-28
Multimodal · Liquid AI · 2025-11-28
Chat · Liquid AI · 2025-11-28
General · ibm-granite · 2025-09-16
General · LG AI · 2025-07-15
Multimodal · Liquid AI · 2025-11-28
General · raidium · 2026-06-15
Multimodal · NCAI · 2025-12-29
Embedding · taide · 2026-06-12
General · Alibaba · 2025-04-27
General · Alibaba · 2025-04-27
Multimodal · zai-org
General · Alibaba
General · Alibaba
Multimodal · openbmb
Reasoning · DeepSeek
Multimodal · datalab-to
General · openbmb
General · hmellor
General · distil-labs
General · farbodtavakkoli
General · ibm-granite
General · Google
Multimodal · lkhl
General · jinaai
Reasoning · typhoon-ai
General · openai
General · paddlepaddle
General · Liquid AI
General · pfnet
General · openbmb
General · baidu
General · amd
General · arcee-ai
General · adamlucek
Coding · shahriarferdoush
General · ahczhg
General · abaryan
General · etherll
General · farbodtavakkoli
General · kamilamila
General · getonit
General · paddlepaddle
General · agentica-org
General · novaciano
General · kgrabko
General · ordenwills
General · smcleish
General · carsenk
Reasoning · nvidia
General · ibm-granite
General · openbmb
General · ibm-granite
General · pyoakum
General · ibm-granite
General · treadon
General · skis-ai-research
General · menlo
General · thkim0305
Reasoning · jackrong
Coding · rahul7star
General · TII
Coding · z-lab
General · osaurusai
General · artificialguybr
General · Microsoft
General · roystar
General · weiboai
General · Microsoft
General · TII
General · tencent
General · primeintellect
General · lgai-exaone · 2025-03-12
Multimodal · Alibaba
Multimodal · rednote-hilab
Multimodal · Google · 2025-06-25
Multimodal · rednote-hilab
General · internlm
General · Alibaba
Reasoning · khazarai
General · bytedance
General · dmusingu
Coding · ibm-granite
General · zero-point-ai
General · bezzam
General · tencent
General · huihui-ai
General · inclusionai
Reasoning · ai21labs
General · Alibaba
General · Alibaba
General · Alibaba
General · ibm-granite
General · Microsoft
Multimodal · opengvlab
Multimodal · nanonets
General · Alibaba
General · voyageai
General · Microsoft
General · farbodtavakkoli
General · farbodtavakkoli
Multimodal · typhoon-ai
General · farbodtavakkoli
General · kristaller486
General · laap-ai
General · jakobhuss
General · farbodtavakkoli
General · Upstage
General · ibm-granite
Coding · DeepSeek
General · weiboai
General · llava-hf
General · tomg-group-umd
General · x-izhang
General · bytedance
General · contextboxai
General · ibm-granite
General · openbmb
General · mrs83
General · onnx-community
Nobody has submitted a benchmark on the M2 Pro 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 16" M2 Max
2x the memory bandwidth, up to 96 GB instead of 32 GB
Newer generationMacBook Pro 16" M5 Pro
1.5x the memory bandwidth, up to 64 GB instead of 32 GB
Used market alternativeMacBook Pro 16" M1 Pro
Same bandwidth and the same memory ceiling
Same chip, other MacMacBook Pro 14" M2 Pro
The same chip in a different Mac
Same chip, other MacMac mini M2 Pro
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 Pro's 200 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 16-inch chassis has the most thermal headroom Apple ships in a laptop, so sustained token throughput stays close to the burst figure. A used M2 Pro at 32 GB still gives you 200 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 M2 Pro MacBook Pro 16" 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 M2 Pro throughput scales with its 200 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 Pro 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: 200 GB/s and up to 32 GB of unified memory are the same numbers today as they were in 2023. A used M2 Pro 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.