# Can I run Qwen2.5-VL 7B on Apple M5 (32GB)?

> **Yes, it runs.** Runs at Q4_K_M using ~7.1 GB of ~21 GB usable. You have room for FP16 for higher quality.

Last validated: 2026-06-15.

## Memory math
- Qwen2.5-VL 7B: 8.29B; Q4_K_M weighs 5.62 GB on disk.
- At Q4_K_M with a 4k context it needs ~7.1 GB (weights + KV cache + ~0.8 GB runtime overhead, ±15% with context length).
- Apple M5 (32GB): 32 GB unified, ~21 GB usable for model weights.
- Headroom: ~13.9 GB; it also fits FP16 for higher quality.

## How to run
Recommended quant: Q4_K_M. Best tool on macOS: LM Studio.

## Run Qwen2.5-VL 7B on other devices
- [Nvidia GeForce RTX 3060 (12GB)](https://localmodel.run/can-i-run/qwen2.5-vl-7b/nvidia-rtx-3060-12gb)
- [Nvidia GeForce RTX 4070 (12GB)](https://localmodel.run/can-i-run/qwen2.5-vl-7b/nvidia-rtx-4070-12gb)
- [Samsung Galaxy S24 Ultra](https://localmodel.run/can-i-run/qwen2.5-vl-7b/samsung-s24-ultra)
- [Generic Android Phone (12GB RAM)](https://localmodel.run/can-i-run/qwen2.5-vl-7b/android-generic-12gb)
- [iPhone 17 Pro](https://localmodel.run/can-i-run/qwen2.5-vl-7b/iphone-17-pro)
- [iPhone Air](https://localmodel.run/can-i-run/qwen2.5-vl-7b/iphone-air)

## Other models that run on Apple M5 (32GB)
- [Qwen2.5 Coder 32B (32B)](https://localmodel.run/can-i-run/qwen2.5-coder-32b/apple-m5-32gb)
- [Granite 4.0 H Small (32B)](https://localmodel.run/can-i-run/granite-4.0-h-small/apple-m5-32gb)
- [Qwen3 30B-A3B (30.5B)](https://localmodel.run/can-i-run/qwen3-30b-a3b/apple-m5-32gb)
- [Gemma 2 27B (27B)](https://localmodel.run/can-i-run/gemma-2-27b/apple-m5-32gb)
- [Gemma 3 27B (27B)](https://localmodel.run/can-i-run/gemma-3-27b/apple-m5-32gb)
- [Mistral Small 3 24B (24B)](https://localmodel.run/can-i-run/mistral-small-3-24b/apple-m5-32gb)

Estimate, not a guarantee. Sources: https://huggingface.co/ggml-org/Qwen2.5-VL-7B-Instruct-GGUF, https://huggingface.co/Qwen/Qwen2.5-VL-7B-Instruct.
More: https://localmodel.run/can-i-run/qwen2.5-vl-7b/apple-m5-32gb