Card × model estimate

Gemma 3 12B on RTX 3090 Ti Q4_K_M

should fit

On an RTX 3090 Ti (24 GB), Gemma 3 12B in Q4_K_M needs about 8,3 Go of video memory: it should fit.

Not measured yet: the figures below are estimates, computed from the models already measured on this card. Measure my card

—

Generation (estimated)

≥ 8,3 Go

Recommended VRAM (24 GB avail.)

—

Power (ref. model)

—

Electricity / M tokens · 0,25 €/kWh

No model has been measured on the RTX 3090 Ti yet: no speed estimate possible.

What about a longer context?

Context	KV cache	Estimated VRAM	Fits in 24 GB?	Estimated speed
4 096	0,3 Go	7,5 Go	yes	—
8 192	0,5 Go	7,8 Go	yes	—
16 384	1,0 Go	8,3 Go	yes	—
32 768	2,0 Go	9,3 Go	yes	—
65 536	4,0 Go	11,3 Go	yes	—
131 072	8,0 Go	15,3 Go	yes	—

Estimated VRAM = file + KV cache (full-attention layers, f16) + ~0,5 Go of buffers, excluding memory used by the system — hence the slightly higher “recommended VRAM”, which keeps that margin. Speed ≈ estimated speed × weights read ÷ (weights read + added KV cache).

Gemma 3 12B on other cards

should fit

Gemma 3 12B page RTX 3090 Ti page Feel the speed Download the GGUF (6,8 Go)

Estimates based on real measurements of other models on this card and on the model's public data (Google Gemma). As soon as a measurement exists, this page shows the real figures.