On an RTX 5070 Ti (16 GB), LFM2.5 1.2B in Q4_K_M needs about 2,2 Go of video memory: it should fit. Estimated generation speed: ≈ 407 tokens/s.
Not measured yet: the figures below are estimates, computed from the models already measured on this card. Measure my card
≈ 407 tok/s
Generation (estimated)
≥ 2,2 Go
Recommended VRAM (16 GB avail.)
≈ 60 W
Power (ref. model)
0,01 €/M tok
Electricity / M tokens · 0,25 €/kWh
Calculation: Qwen3.5 0.8B measured at 514 tok/s on this card, 0,5 Go read per token → × 0,5 Go ÷ 0,7 Go ≈ 407 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
0,0 Go
1,2 Go
yes
≈ 385 tok/s
8 192
0,1 Go
1,3 Go
yes
≈ 361 tok/s
16 384
0,2 Go
1,4 Go
yes
≈ 322 tok/s
32 768
0,4 Go
1,6 Go
yes
≈ 264 tok/s
65 536
0,8 Go
1,9 Go
yes
≈ 195 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 (Petits modèles). As soon as a measurement exists, this page shows the real figures.