On an RTX 5070 Ti (16 GB), Phi-4 reasoning 14B plus in Q4_K_M needs about 9,9 Go of video memory: it should fit. Estimated generation speed: ≈ 84,9 tokens/s.
Not measured yet: the figures below are estimates, computed from the models already measured on this card. Measure my card
≈ 84,9 tok/s
Generation (estimated)
≥ 9,9 Go
Recommended VRAM (16 GB avail.)
≈ 182 W
Power (ref. model)
0,15 €/M tok
Electricity / M tokens · 0,25 €/kWh
Calculation: Phi-4 measured at 84,9 tok/s on this card, 8,4 Go read per token → × 8,4 Go ÷ 8,4 Go ≈ 84,9 tok/s (generation is memory-bound: speed follows the amount of weights read).
What about a longer context?
Context
KV cache
Estimated VRAM
Fits in 16 GB?
Estimated speed
4 096
0,8 Go
9,7 Go
yes
≈ 78,8 tok/s
8 192
1,6 Go
10,5 Go
yes
≈ 72,5 tok/s
16 384
3,1 Go
12,1 Go
yes
≈ 62,6 tok/s
32 768
6,3 Go
15,2 Go
yes
≈ 49,2 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).
Estimates based on real measurements of other models on this card and on the model's public data (Microsoft Phi). As soon as a measurement exists, this page shows the real figures.