Card × model estimate

Phi-3.5 mini 3.8B on RTX 5070 Ti Q4_K_M

should fit

On an RTX 5070 Ti (16 GB), Phi-3.5 mini 3.8B in Q4_K_M needs about 3,7 Go of video memory: it should fit. Estimated generation speed: ≈ 234 tokens/s.

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

≈ 234 tok/s

Generation (estimated)

≥ 3,7 Go

Recommended VRAM (16 GB avail.)

≈ 112 W

Power (ref. model)

0,03 €/M tok

Electricity / M tokens · 0,25 €/kWh

Calculation: Qwen3 2507 4B measured at 224 tok/s on this card, 2,3 Go read per token → × 2,3 Go ÷ 2,2 Go ≈ 234 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 0961,5 Go4,2 Goyes≈ 149 tok/s
8 1923,0 Go5,7 Goyes≈ 105 tok/s
16 3846,0 Go8,7 Goyes≈ 65,3 tok/s
32 76812,0 Go14,7 Goyes≈ 37,3 tok/s
65 53624,0 Go26,7 Gono—
131 07248,0 Go50,7 Gono—

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).

Phi-3.5 mini 3.8B on other cards

should fit
Phi-3.5 mini 3.8B pageRTX 5070 Ti pageFeel the speed Download the GGUF (2,2 Go)

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.