Skip to content

Can you run Gemma 4 12B-it on Radeon RX 6600?

Short answer

Yes, but only just — Gemma 4 12B-it leaves 0.3 GB spare on Radeon RX 6600.

Model file
6.6 GB
Needs in VRAM, with context
about 7.7 GB
Card memory
8 GB
Measured on this hardware
not measured

How this was worked out

Gemma 4 12B-it is a 6.6 GB file. Running it needs the weights in memory plus room for the context window and the runtime, which comes to roughly 7.7 GB in practice. Radeon RX 6600 has 8 GB, which leaves 0.3 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 12B-it on Radeon RX 6600. The closest figure we have is 24 tokens per second on RTX 3060 12 GB, Vulkan backend. 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

0.3 GB is not much of a margin. Your desktop compositor and anything with a video playing are competing for the same memory, so this one loads but can fall back to the CPU under pressure. If it stutters, drop to the next model down. 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

Related