Can you run Gemma 4 31B-it on Radeon RX 7900 XTX?
Short answer
Partly — Gemma 4 31B-it needs about 31.5 GB and Radeon RX 7900 XTX has 24 GB, so some layers run on the CPU.
- Model file
- 30.4 GB
- Needs in VRAM, with context
- about 31.5 GB
- Card memory
- 24 GB
- Measured on this hardware
- not measured
How this was worked out
Gemma 4 31B-it is a 30.4 GB file. Running it needs the weights in memory plus room for the context window and the runtime, which comes to roughly 31.5 GB in practice. Radeon RX 7900 XTX has 24 GB, which leaves -7.5 GB. That is arithmetic rather than a benchmark: it tells you whether the model loads, not how it feels.
What we have actually measured
We have not timed Gemma 4 31B-it on Radeon RX 7900 XTX. The closest figure we have is no measurement of this model at all yet. Rather than scale that number to your card and present the result as a benchmark, this page leaves it out. The method is published at /benchmarks if you would like to run it yourself.
If it is tight
Nightjar will still load Gemma 4 31B-it on Radeon RX 7900 XTX by keeping some layers on the CPU, which works but costs speed. The next model down in the catalogue will fit entirely. Nightjar sizes the context window to the memory it finds, so a smaller card gets a shorter window rather than a failed load.
Smaller models that fit the same card
- Gemma 4 26B-A4B-it on Radeon RX 7900 XTX — 15.8 GB
- Qwen 3.5 27B on Radeon RX 7900 XTX — 15.6 GB
- Qwen 3.5 35B-A3B on Radeon RX 7900 XTX — 20.5 GB
Related
- Up a levelCan your PC run a local AI model?
- Closely relatedCan you run Gemma 4 12B-it on Radeon RX 7900 XTX?
- Closely relatedCan you run Gemma 4 26B-A4B-it on Radeon RX 7900 XTX?
- Closely relatedCan you run Gemma 4 31B-it on Intel Arc A770?
- Closely relatedCan you run Gemma 4 31B-it on Intel Arc B580?
- Elsewhere on the siteLocal AI on Radeon RX 7900 XTX: which models run and how fast
- Elsewhere on the siteGemma 4 31B-it in Nightjar: speed, size and what it is good at