Card × model estimate

R1 Distill 7B Qwen on RTX 5070 Ti Q4_K_M

should fit

On an RTX 5070 Ti (16 GB), R1 Distill 7B Qwen in Q4_K_M needs about 5,9 Go of video memory: it should fit. Estimated generation speed: ≈ 162 tokens/s.

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

≈ 162 tok/s

Generation (estimated)

≥ 5,9 Go

Recommended VRAM (16 GB avail.)

≈ 148 W

Power (ref. model)

0,06 €/M tok

Electricity / M tokens · 0,25 €/kWh

Calculation: Qwen2.5 7B Instruct measured at 162 tok/s on this card, 4,4 Go read per token → × 4,4 Go ÷ 4,4 Go ≈ 162 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 0960,2 Go5,1 Goyes≈ 155 tok/s
8 1920,4 Go5,3 Goyes≈ 148 tok/s
16 3840,9 Go5,7 Goyes≈ 136 tok/s
32 7681,8 Go6,6 Goyes≈ 116 tok/s
65 5363,5 Go8,4 Goyes≈ 90,3 tok/s
131 0727,0 Go11,9 Goyes≈ 62,4 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).

R1 Distill 7B Qwen on other cards

should fit
R1 Distill 7B Qwen pageRTX 5070 Ti pageFeel the speed Download the GGUF (4,4 Go)

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