Fastest
unsloth/gemma-4-E4B-it-qat-GGUF
4B
Highest token generation speed at 205.4 tok/s.
Hardware Benchmarks
Compare RTX 3070 Ti benchmark results and see which models actually earn the best completed quality scores.
GPU-specific specifications for local LLM planning.
Models we recommend for RTX 3070 Ti.
Fastest
4B
Highest token generation speed at 205.4 tok/s.
Best quality & Largest context tested
35B
Highest completed quality score at 88.0. Largest context window tested on this hardware, at 131,072 tokens.
Every model the community ran on this hardware. Up is better answers, right is faster. Time to finish counts every token the model wrote, thinking included, so a model that talks a lot ends up further left.
Medians over 45 fully rated runs of 20 models. Each quantization is its own model.
Which models actually run best on the RTX 3070 Ti, by task, from community benchmark data.
Completed quality-ranked benchmark results for NVIDIA GeForce RTX 3070 Ti.