CanItRun Logocanitrun.

Apple M5 Pro (24GB)

The Apple M5 Pro (24GB) has 24 GB VRAM and 307 GB/s memory bandwidth. It can run 37 of our 81 tracked models natively in VRAM at 8k context.

With 24 GB LPDDR5X, the Apple M5 Pro (24GB) is a laptop-tier GPU that can run 37 models natively. It handles 70B-class models at Q4 quantization.

The Apple M5 Pro (24GB) is the entry point for local LLM inference on the M5 Pro MacBook Pro, with 24GB of unified memory and 307 GB/s bandwidth. Qwen 3.6 27B fits at Q4_K_M with some headroom, and Gemma 4 26B MoE runs efficiently at Q4_K_M — both fully in-memory via MLX and llama.cpp. Qwen 3.6 35B and Gemma 4 31B require CPU offload at this memory tier, but the M5 Pro (24GB) delivers genuine 27B-class on-device AI capability without sacrificing MacBook portability.

Apple M5 Pro (24GB): 2026 entry M5 Pro configuration — 24GB unified LPDDR5X at 307 GB/s, 15-core CPU (5P+10E).

Qwen 3.6 27B fits at Q4_K_M with some headroom, and Gemma 4 26B MoE runs efficiently at Q4_K_M, both fully in-memory. Qwen 3.6 35B and Gemma 4 31B need CPU offload at this tier. ~8-12 t/s for 7B via MLX.

MLX and llama.cpp Metal fully supported. The entry point for genuine 27B-class on-device AI without sacrificing MacBook portability.

VendorApple
ArchitectureApple M5 Pro
CPU cores15 (5S + 10P)
VRAM24 GB (unified)
Memory typeLPDDR5X
Memory bandwidth307 GB/s
Compute backendMETAL
TierLaptop
Released2026
Models (native)37 / 81
Models (offload)0 / 81
Software: MLX gives the best performance on Apple Silicon; llama.cpp Metal backend is a solid alternative. Both are well-supported by Ollama.

Popular models for this GPU

Qwen 3.5 35B-A3B (MoE)Qwen3 32BNemotron 3 Nano 30BQwen3 30B-A3B (MoE)Gemma 2 27B Instruct

Models this GPU runs natively in VRAM (showing 10 of 37)

Too large for this GPU (44)

Explore

Browse all guides →Browse all models →Browse all GPUs →

Frequently asked questions

How much VRAM does the Apple M5 Pro (24GB) have?
The Apple M5 Pro (24GB) has 24 GB of LPDDR5X with 307 GB/s memory bandwidth (unified system memory, shared between CPU and GPU).
What is the Apple M5 Pro (24GB) best for?
With 24 GB of VRAM, the Apple M5 Pro (24GB) is well-suited for running 7B–32B models at Q4 with room for context, making it a great all-rounder for local LLM inference.
What LLMs can the Apple M5 Pro (24GB) run locally?
The Apple M5 Pro (24GB) can run 37 of the 81 open-weight models tracked by CanItRun natively in VRAM at 8k context. Top options include: Llama 3.1 8B Instruct at Q8_0, Llama 3.2 3B Instruct at FP32, Llama 3.2 1B Instruct at FP32.
Can the Apple M5 Pro (24GB) run Llama 3.3 70B Instruct?
The Apple M5 Pro (24GB) does not have enough VRAM to run Llama 3.3 70B Instruct. You would need more VRAM or a lower quantization level.
Can the Apple M5 Pro (24GB) run Qwen 3.6 27B?
Yes. The Apple M5 Pro (24GB) runs Qwen 3.6 27B natively in VRAM at Q3_K_M quantization, achieving approximately 18.2 tokens per second.
Can the Apple M5 Pro (24GB) run Llama 3.1 8B Instruct?
Yes. The Apple M5 Pro (24GB) runs Llama 3.1 8B Instruct natively in VRAM at Q8_0 quantization, achieving approximately 25.6 tokens per second.