The M4 Pro MacBook Pro 14" runs local models at 273 GB/s of memory bandwidth with 24 to 48 GB of unified memory. On Apple Silicon that memory is shared with the GPU, so the whole pool is available for weights: at 48 GB you can hold roughly a 63B 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 44% of the Apple Silicon chips shipped in a Mac, against a 819 GB/s peak.
Its memory ceiling is above 44% 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.
3,352 of 3,641 models fit, and 3,007 of them run with headroom rather than as a squeeze.
3,503 of 3,641 models fit, and 3,351 of them run with headroom rather than as a squeeze.
Every model in the database against this exact configuration, at 273 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 · NCAI · 2025-12-29
Chat · Liquid AI · 2025-11-28
General · ibm-granite · 2025-09-16
General · Liquid AI · 2025-11-28
General · Liquid AI · 2025-11-28
Multimodal · NCAI · 2025-12-29
Reasoning · HuggingFace · 2025-07-08
Multimodal · Liquid AI · 2025-11-28
Multimodal · Liquid AI · 2025-11-28
Multimodal · Liquid AI · 2025-11-28
Reasoning · jackrong · 2026-03-16
Multimodal · Google · 2025-07-30
Multimodal · Google · 2025-06-25
General · LG AI · 2025-07-15
Multimodal · Liquid AI · 2025-11-28
General · lgai-exaone · 2025-03-12
General · raidium · 2026-06-15
Embedding · taide · 2026-06-12
General · Alibaba · 2025-04-27
General · Alibaba · 2025-04-27
Multimodal · zai-org
Multimodal · Alibaba
General · Alibaba
General · Alibaba
Multimodal · openbmb
Reasoning · DeepSeek
Multimodal · datalab-to
General · openbmb
General · hmellor
General · distil-labs
General · farbodtavakkoli
General · Liquid AI
General · ibm-granite
General · Google
Multimodal · lkhl
General · jinaai
General · Alibaba
Reasoning · typhoon-ai
General · Upstage
General · openai
General · paddlepaddle
General · Liquid AI
General · pfnet
General · openbmb
General · baidu
General · amd
General · bytedance-seed
General · arcee-ai
General · adamlucek
Coding · shahriarferdoush
General · ahczhg
General · abaryan
General · etherll
General · farbodtavakkoli
Reasoning · khazarai
General · kamilamila
General · getonit
General · paddlepaddle
General · agentica-org
General · novaciano
General · dmusingu
General · kgrabko
General · ordenwills
General · smcleish
General · carsenk
Reasoning · nvidia
General · zero-point-ai
General · ibm-granite
General · openbmb
General · ibm-granite
General · osaurusai
General · pyoakum
General · ibm-granite
General · treadon
General · tencent
General · skis-ai-research
General · menlo
General · thkim0305
Reasoning · jackrong
General · huihui-ai
Coding · rahul7star
General · inclusionai
General · TII
Coding · z-lab
General · osaurusai
General · artificialguybr
General · Microsoft
General · roystar
General · weiboai
General · Microsoft
General · TII
General · tencent
General · primeintellect
Multimodal · Alibaba
Multimodal · Microsoft
Multimodal · rednote-hilab
General · ibm-granite
Multimodal · rednote-hilab
Multimodal · nanonets
Multimodal · ibm-granite
Multimodal · typhoon-ai
General · internlm
Multimodal · goekdeniz-guelmez
General · kristaller486
General · ibm-granite
General · weiboai
General · x-izhang
General · bytedance
General · ibm-granite
General · bllossom
General · opengvlab
General · bytedance
General · radheneev
Reasoning · jackrong
General · NousResearch
Reasoning · nvidia
General · inference-net
General · opengvlab
Reasoning · nvidia
General · ibm-granite
Coding · ibm-granite
Reasoning · iffyuan
General · bezzam
General · huihui-ai
General · magistrtheone
Both bins run the same 273 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, 16-core GPU | 273 GB/s | 24, 48 GB | Identical |
| 14-core CPU, 20-core GPU | 273 GB/s | 24, 48 GB | Identical |
Nobody has submitted a benchmark on the M4 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 14" M4 Max
2x the memory bandwidth, up to 128 GB instead of 48 GB
Newer generationMacBook Pro 14" M5 Pro
1.1x the memory bandwidth, up to 64 GB instead of 48 GB
Used market alternativeMacBook Pro 14" M3 Pro
45% less memory bandwidth, 36 GB ceiling instead of 48 GB
Same chip, other MacMacBook Pro 16" M4 Pro
The same chip in a different Mac
Same chip, other MacMac mini M4 Pro
The same chip, but it takes up to 64 GB here instead of 48 GB
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 Pro's 273 GB/s bus is shared by CPU, GPU, and Neural Engine, so a 48 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 M4 Pro at 48 GB still gives you 273 GB/s and a hard 63B 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 Pro MacBook Pro 14" tops out at 48 GB, which leaves about 42 GB for weights. The practical ceiling on this machine is around 63B parameters at Q4.
Memory is the only spec that changes what you can run at all. 24 GB holds about a 31B model at Q4; 48 GB holds about 63B. 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 Pro throughput scales with its 273 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 Pro 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 273 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: 273 GB/s and up to 48 GB of unified memory are the same numbers today as they were in 2024. A used M4 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.