Can I run Qwen3-8B on a Radeon RX 9070 XT?

Yes, with a GGUF version

The published weights are too big, but the Q8_0 file from Qwen/Qwen3-8B-GGUF (8.71 GB) fits, with room for ≈ 38K tokens of context.

Full analysis of Qwen3-8B Everything that runs on Radeon RX 9070 XT Get the Q8_0 file on Hugging Face

ollama run hf.co/Qwen/Qwen3-8B-GGUF:Q8_0

Files and context on Radeon RX 9070 XT

Each file of Qwen3-8B (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 9070 XT	Context (16-bit)	Context (8-bit)
As published	16.4 GB	Doesn't fit	—	—
Q8_0Qwen/Qwen3-8B-GGUF	8.71 GB	Fits	38K	40K
Q6_KQwen/Qwen3-8B-GGUF	6.73 GB	Fits	40K	40K
Q5_K_MQwen/Qwen3-8B-GGUF	5.85 GB	Fits	40K	40K
Q5_0Qwen/Qwen3-8B-GGUF	5.72 GB	Fits	40K	40K
Q4_K_MQwen/Qwen3-8B-GGUF	5.03 GB	Fits	40K	40K

Qwen3-8B on other hardware

Popular models that run on Radeon RX 9070 XT

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.