NVIDIA GeForce RTX 3070 Ti
Ampere Ti with GDDR6X at 608 GB/s. 8 GB VRAM is the ceiling — same as base 3070, no improvement on the variable that matters. Runs 7B Q4 at ~110-145 tok/s with ExLlamaV2 thanks to bandwidth + Tensor compute. Used $320-380. The 'paid for the Ti suffix, got the same 8 GB' card; only worth it over the base 3070 if buying new.
Extrapolated from 608 GB/s bandwidth — 73.0 tok/s estimated. No measured benchmarks yet.
Plain-English: Comfortable for 7B chat.
Verdicts extrapolated from catalog VRAM + bandwidth + ecosystem flags. Hover any chip for the rationale. Want measured numbers? Submit your own run with runlocalai-bench --submit.
This card is for the operator who already owns a 3070 and wants a modest inference speed bump without changing VRAM constraints. It runs 7B Q4 models at ~110-145 tok/s with ExLlamaV2, and can handle 13B Q4 at ~60-80 tok/s. The 8 GB VRAM ceiling breaks on 30B+ models, and even 13B Q4 with a 4K context leaves little headroom. Pass if you need to run 13B with long context or any 30B class model—the 8 GB limit is the same as the base 3070. At ~$350 used, the Ti suffix adds ~15% bandwidth over the 3070 for ~$50-80 more, which is fair only if you're buying new and need that extra speed.
›Why this rating
The 3070 Ti offers strong 7B performance but is hamstrung by 8 GB VRAM, limiting its utility for larger models. It's a marginal upgrade over the 3070, and the price premium only makes sense for new buyers who can't find a 3070.
Overview
Ampere Ti with GDDR6X at 608 GB/s. 8 GB VRAM is the ceiling — same as base 3070, no improvement on the variable that matters. Runs 7B Q4 at ~110-145 tok/s with ExLlamaV2 thanks to bandwidth + Tensor compute. Used $320-380. The 'paid for the Ti suffix, got the same 8 GB' card; only worth it over the base 3070 if buying new.
Search-fallback links. Editorial hasn't yet curated retailer URLs for this card. Approx. $350.
Some links above are affiliate links. We may earn a commission at no extra cost to you. How we make money.
Specs
| VRAM | 8 GB |
| Power draw | 290 W |
| Released | 2021 |
| MSRP | $599 |
| Backends | CUDA Vulkan |
Models that fit
Open-weight models small enough to run on NVIDIA GeForce RTX 3070 Ti with usable context.
Frequently asked
What models can NVIDIA GeForce RTX 3070 Ti run?
Does NVIDIA GeForce RTX 3070 Ti support CUDA?
How much does NVIDIA GeForce RTX 3070 Ti cost?
Where next?
Reviewed by RunLocalAI Editorial. See our editorial policy for how we research and verify hardware specifications.