# Can I run Qwen2.5 32B on AMD Radeon RX 7900 XTX (24GB)?

Updated: 2026-06-15

**Yes, but tight.** Fits at Q4_K_M (~22.1 GB of ~23 GB usable) but with little headroom, close other apps.

- Model: 32B, Q4_K_M 19.85 GB
- Device: 24 GB vram, ~23 GB usable for weights
- Needs ~22.1 GB at Q4_K_M; recommended quant: Q4_K_M
- Best tool on Windows: LM Studio
- Command: `ollama run qwen2.5:32b`

Estimate. Method: weights + KV cache + ~0.8GB overhead. Sources: https://ollama.com/library/qwen2.5, https://huggingface.co/bartowski/Qwen2.5-32B-Instruct-GGUF, https://qwenlm.github.io/blog/qwen2.5/.

More: https://localmodel.run/can-i-run/qwen2.5-32b/amd-rx-7900-xtx-24gb