LOCAL AIregistry
‹ all GPUs

RTX 3070 Ti

NVIDIA · 8 GB · 608 GB/s
Top 2 recipes
Recommended
Qwen3.5-9B
EXL3 3 bpwTabbyAPI64K context

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

105 tok/sdecode
1,485 tok/sprefill
64Kcontext
✓ Thinks✓ Tools✓ Long context
Tested on this card · Sep 25, 2026
Another family
Gemma 4 12B
EXL3 3 bpwTabbyAPI32K context

Best for Vision, documents and quick chat.

47 tok/sdecode
967 tok/sprefill
32Kcontext
✓ Thinks✓ Tools✓ Long context✓ Vision
Tested on this card · Sep 26, 2026