AppleMac / unified memoryCurrent

Apple M5 Pro for local LLMs

Name: LLM Configurator — GPU VRAM Checker
Author: LLM Configurator

Written by Jakub Rusinowski · Last updated July 12, 2026

With 64 GB at 307 GB/s, the M5 Pro runs 126 catalogued models at Q4_K_M with 8K context. The largest that fits is Llama 3.3 70B Instruct (~45.7 GB), and the top pick is K2 Horizon MoVA 36B-A4B at 24–50 tok/s.

Up to 64 GB unified memory at 307 GB/s — double the memory ceiling of the M4 Pro. Released March 2026 in the MacBook Pro 14"/16". Comfortably fits 32B models at Q4.

Check my hardware →Full benchmark table

Models that run on the M5 Pro

Q4_K_M, 8K context, 48 GB usable. Ranked by quality and speed.

Model	VRAM	Speed	Fit
K2 Horizon MoVA 36B-A4B K2 Horizon	25 GB	24–50 tok/s	Fits
Qwen 3.6 35B-A3B Qwen 3.6	22.2 GB	43–89 tok/s	Fits
Nex-N2.5 mini Nex-N2.5	21.9 GB	26–54 tok/s	Fits
Nex-N2 mini Nex-N2	21.9 GB	26–54 tok/s	Fits
Qwen 3.5 35B-A3B Qwen 3.5	21.9 GB	26–54 tok/s	Fits
Laguna XS 2.1 33B-A3B Poolside Laguna XS 2.1	20.7 GB	26–55 tok/s	Fits
Granite 4.0 Small-H 32B-A9B IBM Granite 4.0	20.1 GB	14–29 tok/s	Fits
Nemotron-Cascade 2 30B-A3B Nemotron Cascade 2	19.9 GB	25–51 tok/s	Fits
Qwen 3 30B-A3B (MoE) Qwen 3	20 GB	33–69 tok/s	Fits
Qwen3-Coder 30B-A3B (MoE) Qwen3-Coder	20 GB	33–69 tok/s	Fits
GLM-4.7-Flash 30B-A3B GLM-4.7 / GLM-Z1	18.9 GB	27–55 tok/s	Fits
Nemotron 3 Nano Omni 30B-A3B Nemotron 3 Nano Omni	18.9 GB	27–55 tok/s	Fits

Showing 12 of 126

Buy it or rent the same memory

Buy the card, or rent a GPU with the same memory by the hour to try models first.

Buy this hardware Apple MacBook Pro M5 Pro — 48 GB unified memory · 307 GB/s Deploy in the cloud now NVIDIA A100 80GB on RunPod — from $1.39/hr · rate checked 2026-07

or compare on Vast.ai from $0.77/hr (typical low · varies)

As an Amazon Associate we earn from qualifying purchases. Cloud GPU links are referral links — we may earn a commission at no extra cost to you.

Affiliate disclosure: Some links on this page are affiliate links — if you buy through them, LLM Configurator may earn a commission at no extra cost to you. As an Amazon Associate, LLM Configurator earns from qualifying purchases.

Apple MacBook Pro M5 Pro

48 GB unified memory · 307 GB/s

2026 prices are volatile — check the current listing.

Check price on Amazon

Speed vs other GPUs

Llama 3.1 8B, Q4_K_M. Estimated ranges. How this is calculated

RTX PRO 5000 Blackwell (72 GB)94–194 tok/s M5 Ultra59–123 tok/s M3 Ultra43–90 tok/s M1 Ultra43–89 tok/s M2 Ultra43–89 tok/s M5 Max34–71 tok/s M4 Max31–64 tok/s M5 Max (32-core GPU)27–56 tok/s M5 Pro19–39 tok/s

Specifications

Specs last updated 2026-07-12.

Memory: 64 GB
Memory bandwidth: 307 GB/s
Architecture: ARM, 3nm TSMC
Series: Apple Silicon
Board power: 30 W
Release year: 2026
Usable for models: 48 GB (~75% of unified)

Best for14B–32B modelsMacBook Pro 14"/16"developers

Recommended first model (Ollama)

Frequently asked questions

Can the Apple M5 Pro run local LLMs?

Yes. With 64 GB (48 GB usable by a model) it runs 126 of the catalogued models at Q4_K_M with 8K context; the largest is Llama 3.3 70B Instruct, needing about 45.7 GB.

How fast is the Apple M5 Pro for AI inference?

It is estimated to run Llama 3.1 8B at 19–39 tok/s at Q4_K_M. Llama 3.3 70B is estimated at 2.5–5.1 tok/s. These are modelled estimates from memory bandwidth, not measurements; the methodology page shows the formula.

What LLMs can I run on 64 GB?

Among the best that fit: K2 Horizon MoVA 36B-A4B, Qwen 3.6 35B-A3B, Nex-N2.5 mini, Nex-N2 mini, Qwen 3.5 35B-A3B. The quickest start is Ollama: ollama run qwen3:14b.