M4 Pro
81 AI models fit in 24 GB VRAM at Q4 native. 7 more run with CPU offloading. Real benchmarks below.
llama.cpp 0.2.x · CUDA 12 · Ubuntu 22.04 · Prices verified on Amazon · methodology →
Execution Context
Ver oferta atual
Amazon affiliate link for M4 Pro
Alguns links são links de afiliado da Amazon. Podemos receber uma comissão sem custo adicional para si. O cookie da Amazon pode durar até 24 horas após o clique.
Full Specifications
Apple · 2024-10
| VRAM | 24 GB Unified Memory |
| Bandwidth | 273 GB/s |
| FP16 TFLOPS | 9.2 |
| AI Score | 50 / 140 |
| Tensor Cores | 16 |
| TDP | 35 W |
| Price Band | Integrada |
| Released | 2024-10 |
AI Benchmarks
Real inference measurements — llama.cpp Q4_K_M
| Task | Result |
|---|---|
| Llama 1B Q4 | 143 tok/s |
| Llama 3B Q4 | 57 tok/s |
| Llama 7B Q4 | 45 tok/s |
| Llama 13B Q4 | 13 tok/s |
| Llama 30B Q4 | 6 tok/s |
| Llama 70B Q4 | Offload or multi-GPU |
| Stable Diffusion 512px | 7.5s / img |
| Whisper Large RTF | 0.7x |
RTF < 1.0 = faster than real time. For Stable Diffusion and Whisper lower is better; for tokens/s higher is better.
Compare M4 Pro with another GPU
Is an upgrade worth it? Compare specs and real benchmarks side by side.
Open comparator →Compatible AI Models — M4 Pro
81 models run fully in VRAM · 7 with CPU offloading
Flux.1 Dev
Whisper Large V3
Stable Diffusion 3.5 Large
FLUX.2 Dev
Qwen2.5-Coder 32B
DeepSeek R1 Distill 32B
Qwen2.5 32B
Stable Diffusion 3.5 Medium
Show all 81 compatible models →
Also runs with CPU offloading (7)
- Llama 3.3 70B 21 GB Q2 How to install →
- Qwen2.5 72B 21 GB Q2 How to install →
- Llama 3.1 70B 20 GB Q2 How to install →
- Qwen3-Coder-Next 80B-A3B 22 GB Q2 How to install →
- Mixtral 8x7B 14 GB Q2 How to install →
- Hermes 3 70B 20 GB Q2 How to install →
- Nous Hermes 2 Mixtral 8x7B 13 GB Q2 How to install →
M4 Pro · Amazon
Os precos de GPU mudam com frequencia entre lojas. Consulte a oferta atual antes de comprar.
Ver oferta atualAlguns links são links de afiliado da Amazon. Podemos receber uma comissão sem custo adicional para si. O cookie da Amazon pode durar até 24 horas após o clique.
M4 Pro for Local AI
La M4 Pro con 24GB de Unified Memory es una GPU de alto rendimiento para IA local. Puede ejecutar modelos de 7B, 13B y hasta 70B parámetros en cuantización Q2, cubriendo la mayoría de los casos de uso prácticos: asistentes de chat, generación de código, análisis de texto y generación de imágenes con Stable Diffusion.
En benchmarks reales, la M4 Pro alcanza 45 tokens/segundo en Llama 7B Q4 — velocidad suficiente para conversación fluida en tiempo real. Los modelos de 13B como Phi-4 o Qwen2.5 14B corren cómodamente en Q4, y modelos 70B son accesibles via Q2 con 7 opciones.
La relación rendimiento-precio de la M4 Pro la hace una de las mejores opciones para usuarios técnicos que quieren IA local seria. Usa la calculadora de VRAM para ver exactamente qué cuantización necesita cada modelo, o consulta nuestra guía para elegir GPU.
Plan your full AI build
M4 Pro · 24 GB VRAM — configure PSU, RAM, storage and check compatible models.
Related articles
Not sure which model to run on your M4 Pro?
The VRAM calculator tells you exactly which quantization you need.
Get the best price for M4 Pro
Open Amazon with our affiliate link and check availability, variants, and current deals.