Can I run Qwen3-VL-8B-Thinking on a Radeon RX 7900 XTX?

Yes, just

Its published weights (17.5 GB) fit in the 21.6 GB a Radeon RX 7900 XTX can use, with room for ≈ 27K tokens of context.

Full analysis of Qwen3-VL-8B-Thinking Everything that runs on Radeon RX 7900 XTX Get the weights on Hugging Face

hf download Qwen/Qwen3-VL-8B-Thinking

Files and context on Radeon RX 7900 XTX

Each file of Qwen3-VL-8B-Thinking (and of GGUF versions the site has analyzed), and how much context fits next to it, with the context cache in 16-bit or 8-bit.

File	Size	On Radeon RX 7900 XTX	Context (16-bit)	Context (8-bit)
As published	17.5 GB	Tight	27K	54K
F16Qwen/Qwen3-VL-8B-Thinking-GGUF	16.4 GB	Fits	35K	69K
Q8_0Qwen/Qwen3-VL-8B-Thinking-GGUF	8.71 GB	Fits	85K	171K
Q4_K_MQwen/Qwen3-VL-8B-Thinking-GGUF	5.03 GB	Fits	110K	220K

Qwen3-VL-8B-Thinking on other hardware

Popular models that run on Radeon RX 7900 XTX

Assumes 90% of the card's memory is usable and at least 4K tokens of context for one conversation, with the context cache in 16-bit unless noted. Fits leaves at least 20% of that memory for context; Tight leaves less.