RTX 5070 Ti

NVIDIA · 16 GB · 896 GB/s

Top 3 recipes

Recommended

Qwen3.8-27B

EXL3 3 bpwTabbyAPI128K context

Best for Coding agents, long documents, everyday assistant work.

94 tok/sdecode

916 tok/sprefill

128Kcontext

✓ Thinks✓ Tools✓ Long context✓ Vision

Tested on this card · Sep 25, 2026

Fastest

Qwen3.5-9B

EXL3 6 bpwTabbyAPI128K context

Best for Fast answers and light agent work on 8–12 GB cards.

163 tok/sdecode

2,566 tok/sprefill

128Kcontext

✓ Thinks✓ Tools✓ Long context

Tested on this card · Sep 26, 2026

Another family

Gemma 4 26B A4B

EXL3 3.1 bpwTabbyAPI32K context

Best for Fast multimodal work on 16–24 GB cards.

97 tok/sdecode

1,799 tok/sprefill

32Kcontext

✓ Thinks✓ Tools✓ Long context✓ Vision

Tested on this card · Sep 26, 2026