Skip to content
localmodel.run

image model · qwen · Windows

Can I run Qwen-Image on AMD Radeon RX 7900 XTX (24GB)?

Compatibility verdict VRAM check
Yes, it runsfast on this GPU

Yes. Qwen-Image runs on AMD Radeon RX 7900 XTX (24GB) at Q4_K_M GGUF (~14 GB of ~23 GB usable).

Needs ~14 GB Device usable ~23 GB

Runs at Q4_K_M GGUF using ~14 GB of ~23 GB usable.

Peak VRAM
~14 GB
Usable on device
~23 GB
Device memory
24 GB
Quant
Q4_K_M GGUF

How to run it

Use ComfyUI or Nunchaku (SVDQuant 4-bit) at Q4_K_M GGUF. The big text encoder is loaded to encode your prompt, then offloaded before generation, which is why peak VRAM stays near the backbone size rather than the sum of every file.

Model qwen
Type
image (MMDIT)
Parameters
20B
Peak VRAM
~14 GB at Q4_K_M GGUF
Resolution
1328×1328
License
Apache-2.0
Full Qwen-Image requirements →
Device Windows
Memory
24 GB vram
Usable for weights
~23 GB
Best runtime
Ollama (ROCm) / llama.cpp ROCm (Linux)
Best models for AMD Radeon RX 7900 XTX (24GB) →

You could also run

Run Qwen-Image on other hardware

FAQ

Can AMD Radeon RX 7900 XTX (24GB) run Qwen-Image?

Yes. Qwen-Image runs on AMD Radeon RX 7900 XTX (24GB) at Q4_K_M GGUF (~14 GB of ~23 GB usable).

How much VRAM does Qwen-Image need?

AMD Radeon RX 7900 XTX (24GB) has room to spare. At Q4_K_M GGUF the realistic peak is ~14 GB of VRAM, versus ~57 GB with every component kept resident (no offload). With aggressive CPU offload it drops to ~3 GB, much slower.

What do I use to run Qwen-Image locally?

Qwen-Image runs in ComfyUI or Nunchaku (SVDQuant 4-bit). It loads as a diffusion checkpoint plus its text encoder and VAE, not a single chat command.

Sources

VRAM figures are sourced peak-usage anchors at the noted quant, validated 2026-06-15. See methodology.