community-verified · measured pool data

Can the RTX 3090 24GB run gemma-4-12B-it-GGUF?

Yes — community-measured at 57 tok/s (4 runs at 4-bit).

Verified single-stream runs on the RTX 3090 24GB from the localmaxxing public pool. Every number on this page is measured — nothing here is estimated.

Quantization	Median tok/s	TTFT (ms)	Peak VRAM	Max context tested	Engines
4-bit	57	951.4	—	2,048	llama.cpp

Go deeper

I have a goal — find models that fit my use case → I have hardware — browse everything my rig can run → All machine × model answer pages →