Qwen2.5 72B Instruct (Q5_K_M) — 15.4 GBon Apple M2 Pro 16GB
Overview
Qwen2.5 72B Instruct is a 72.71B parameter dense language model by Qwen, with code, multilingual, tool-calls capabilities. It supports a context window of up to 32,768 tokens.
Qwen2.5 72B Instruct is a 72.71-billion-parameter dense transformer from Alibaba's Qwen team, fine-tuned for instruction following, code generation, and multilingual tasks. It competes with other leading 70B instruct models while supporting 14 languages including English, Chinese, Arabic, and Japanese. The model provides native tool calling and structured output capabilities. With a 32K context window and grouped-query attention, it quantizes efficiently for self-hosted inference on high-end consumer or server-class GPU configurations.
At Q5_K_M quantization (medium quality tier), the model weighs 48.1 GB. This exceeds the 16 GB of VRAM on Apple M2 Pro 16GB. Inference is still possible via CPU offload or memory-mapped loading from disk, but expect significantly reduced performance.
Hardware Requirements
| Model size | 48.1 GB |
| VRAM available | 16 GB |
| VRAM used | 15.4 GB |
| System RAM | |
| Min RAM required | 34.3 GB |
| GPU layers | 23 / 80 |
| Context size | 1,069 |
| Backend | metal |
| Flash attention | Yes |
| Reading from disk | Yes |
Performance Notes
Deploy
Install llama.cpp
brew install llama.cppDownload Model
curl -L -o qwen2-5-72b-instruct.gguf "https://huggingface.co/Qwen/Qwen2.5-72B-Instruct-GGUF/resolve/main/qwen2.5-72b-instruct-q5_k_m-00001-of-00014.gguf"Start Server
llama-server \
-m qwen2-5-72b-instruct.gguf \
--n-gpu-layers 23 \
--ctx-size 1069 \
--flash-attnVerify
curl http://localhost:8080/healthFrequently Asked Questions
How much VRAM does Qwen2.5 72B Instruct (Q5_K_M) need?
The Q5_K_M quantization of Qwen2.5 72B Instruct requires 48.1 GB. 23 of 80 layers fit in the 16 GB of VRAM on Apple M2 Pro 16GB; remaining layers are offloaded to CPU.
Can I run Qwen2.5 72B Instruct on Apple M2 Pro 16GB?
Yes, with reduced performance. Apple M2 Pro 16GB can run Qwen2.5 72B Instruct (Q5_K_M), but only 23 of 80 layers fit in VRAM. The rest are offloaded to CPU.
What is quantization?
Quantization reduces a model's numerical precision from its original floating-point format to a more compact representation. This shrinks the file size and VRAM footprint, making it possible to run large models on consumer hardware. The trade-off is a small reduction in output quality. Q5_K_M compresses Qwen2.5 72B Instruct from its original size down to 48.1 GB.
What quantization should I choose for Qwen2.5 72B Instruct?
Q5_K_M is a medium-quality quantization. Higher-quality quants (Q8, Q6) preserve more model accuracy but need more VRAM. Lower quants (Q4, Q3, Q2) reduce VRAM usage at the cost of some quality. Choose based on your available hardware and quality requirements.
What is flash attention and why is it enabled?
Flash attention is a memory-efficient algorithm that speeds up the attention mechanism in transformer models. It reduces VRAM usage during inference by avoiding the materialisation of the full attention matrix. For Qwen2.5 72B Instruct on Apple M2 Pro 16GB, flash attention is enabled to maximise context length and throughput within the available 16 GB of VRAM.
Why are some layers offloaded to CPU?
Apple M2 Pro 16GB has 16 GB of VRAM, but Qwen2.5 72B Instruct (Q5_K_M) requires approximately 48.1 GB. Only 23 of 80 layers fit in VRAM; the remaining layers run on CPU, which is slower but still functional.
How do I run Qwen2.5 72B Instruct (Q5_K_M) with Ollama?
Run ollama run qwen2.5:72b-instruct-q5_k_m to start Qwen2.5 72B Instruct (Q5_K_M). Ollama handles downloading the model weights automatically on first run.