Card × model estimate

Gemma 4 E4B on RTX 5070 Ti Q4_K_M

should fit

On an RTX 5070 Ti (16 GB), Gemma 4 E4B in Q4_K_M needs about 6,5 Go of video memory: it should fit. Estimated generation speed: ≈ 136 tokens/s.

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

≈ 136 tok/s

Generation (estimated)

≥ 6,5 Go

Recommended VRAM (16 GB avail.)

≈ 154 W

Power (ref. model)

0,08 €/M tok

Electricity / M tokens · 0,25 €/kWh

Calculation: Qwen3 8B measured at 146 tok/s on this card, 4,7 Go read per token → × 4,7 Go ÷ 5,0 Go ≈ 136 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 Go5,6 Goyes≈ 134 tok/s
8 1920,1 Go5,6 Goyes≈ 133 tok/s
16 3840,2 Go5,8 Goyes≈ 130 tok/s
32 7680,4 Go6,0 Goyes≈ 125 tok/s
65 5360,9 Go6,4 Goyes≈ 116 tok/s
131 0721,8 Go7,3 Goyes≈ 101 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 4 E4B on other cards

should fit
Gemma 4 E4B pageRTX 5070 Ti pageFeel the speed Download the GGUF (5,0 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.