Can I run Qwen3.8-27B-AP-GGUF on a Radeon RX 9070 XT?

Yes, just

Its Q3_K_XL file (13.1 GB) fits in the 14.4 GB a Radeon RX 9070 XT can use, with room for ≈ 16K tokens of context.

Full analysis of Qwen3.8-27B-AP-GGUF Everything that runs on Radeon RX 9070 XT Get the Q3_K_XL file on Hugging Face

ollama run hf.co/agentionai/Qwen3.8-27B-AP-GGUF:Q3_K_XL

Files and context on Radeon RX 9070 XT

Each file of Qwen3.8-27B-AP-GGUF (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)
Q4_K_XL	17.6 GB	Doesn't fit	—	—
Q4_K_M	16.5 GB	Doesn't fit	—	—
IQ4_XS	14.3 GB	Doesn't fit	—	—
Q3_K_XL	13.1 GB	Tight	16K	33K
IQ3_S	12.0 GB	Tight	33K	66K
IQ3_XS	11.5 GB	Fits	41K	82K
IQ3_XXS	10.7 GB	Fits	52K	105K
IQ2_S	9.61 GB	Fits	69K	138K

Qwen3.8-27B-AP-GGUF 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.