Card × model estimate

Gemma 3n E4B on RTX 5070 Ti Q4_K_M

should fit

On an RTX 5070 Ti (16 GB), Gemma 3n E4B in Q4_K_M needs about 5,4 Go of video memory: it should fit. Estimated generation speed: ≈ 179 tokens/s.

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

≈ 179 tok/s

Generation (estimated)

≥ 5,4 Go

Recommended VRAM (16 GB avail.)

≈ 148 W

Power (ref. model)

0,06 €/M tok

Electricity / M tokens · 0,25 €/kWh

Calculation: Qwen2.5 7B Instruct measured at 162 tok/s on this card, 4,4 Go read per token → × 4,4 Go ÷ 3,9 Go ≈ 179 tok/s (generation is memory-bound: speed follows the amount of weights read).

What about a longer context?

ContextKV cacheEstimated VRAMFits in 16 GB?Estimated speed
4 0960,1 Go4,5 Goyes≈ 177 tok/s
8 1920,1 Go4,6 Goyes≈ 175 tok/s
16 3840,2 Go4,7 Goyes≈ 170 tok/s
32 7680,4 Go4,9 Goyes≈ 162 tok/s

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 3n E4B on other cards

should fit
Gemma 3n E4B pageRTX 5070 Ti pageFeel the speed Download the GGUF (3,9 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.