On an RTX 5070 Ti (16 GB), Granite 3.3 8B in Q4_K_M needs about 6,1 Go of video memory: it should fit. Estimated generation speed: ≈ 150 tokens/s.
Not measured yet: the figures below are estimates, computed from the models already measured on this card. Measure my card
≈ 150 tok/s
Generation (estimated)
≥ 6,1 Go
Recommended VRAM (16 GB avail.)
≈ 148 W
Power (ref. model)
0,07 €/M tok
Electricity / M tokens · 0,25 €/kWh
Calculation: Meta Llama 3.1 8B Instruct measured at 151 tok/s on this card, 4,6 Go read per token → × 4,6 Go ÷ 4,6 Go ≈ 150 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
0,6 Go
5,7 Go
yes
≈ 134 tok/s
8 192
1,3 Go
6,4 Go
yes
≈ 120 tok/s
16 384
2,5 Go
7,6 Go
yes
≈ 98,5 tok/s
32 768
5,0 Go
10,1 Go
yes
≈ 72,6 tok/s
65 536
10,0 Go
15,1 Go
yes
≈ 47,6 tok/s
131 072
20,0 Go
25,1 Go
no
—
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 (IBM Granite). As soon as a measurement exists, this page shows the real figures.