Can I run gemma-4-12B-coder-fable5-composer2.5-v1-GGUF on a Radeon RX 9070 XT?

Yes, just

Its Q8_0 file (12.7 GB) fits in the 14.4 GB a Radeon RX 9070 XT can use, with room for ≈ 8K tokens of context.

Full analysis of gemma-4-12B-coder-fable5-composer2.5-v1-GGUF Everything that runs on Radeon RX 9070 XT Get the Q8_0 file on Hugging Face

ollama run hf.co/yuxinlu1/gemma-4-12B-coder-fable5-composer2.5-v1-GGUF:Q8_0

Files and context on Radeon RX 9070 XT

Each file of gemma-4-12B-coder-fable5-composer2.5-v1-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)
Q8_0	12.7 GB	Tight	8K	21K
Q6_K	9.79 GB	Fits	29K	64K
Q4_K_M	7.38 GB	Fits	47K	100K
Q3_K_M	6.09 GB	Fits	57K	119K
Q2_K	4.83 GB	Fits	66K	138K

gemma-4-12B-coder-fable5-composer2.5-v1-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.