Card × model estimate

Qwen3 2507 4B on RTX 4070 Ti Q4_K_M

should fit

On an RTX 4070 Ti (12 GB), Qwen3 2507 4B in Q4_K_M needs about 3,8 Go of video memory: it should fit. Estimated generation speed: ≈ 158 tokens/s.

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

≈ 158 tok/s

Generation (estimated)

≥ 3,8 Go

Recommended VRAM (12 GB avail.)

≈ 137 W

Power (ref. model)

0,06 €/M tok

Electricity / M tokens · 0,25 €/kWh

Calculation: Phi-4 mini 3.8B measured at 159 tok/s on this card, 2,3 Go read per token → × 2,3 Go ÷ 2,3 Go ≈ 158 tok/s (generation is memory-bound: speed follows the amount of weights read).

What about a longer context?

ContextKV cacheEstimated VRAMFits in 12 GB?Estimated speed
4 0960,6 Go3,4 Goyes≈ 132 tok/s
8 1921,1 Go4,0 Goyes≈ 110 tok/s
16 3842,3 Go5,1 Goyes≈ 82,1 tok/s
32 7684,5 Go7,3 Goyes≈ 54,7 tok/s
65 5369,0 Go11,8 Goyes≈ 32,8 tok/s
131 07218,0 Go20,8 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).

Qwen3 2507 4B on other cards

should fit
Qwen3 2507 4B pageRTX 4070 Ti pageFeel the speed Download the GGUF (2,3 Go)

Estimates based on real measurements of other models on this card and on the model's public data (Qwen). As soon as a measurement exists, this page shows the real figures.