Fastest
lmstudio-community/lfm2.5-2.6b
2.6B
165.9 tok/s
Highest token generation speed at 165.9 tok/s.
Hardware Benchmarks
Best Local LLM Performance for RTX 4070 Ti Super
Compare RTX 4070 Ti Super benchmark results and see which models actually earn the best completed quality scores.
Hardware Overview
GPU-specific specifications for local LLM planning.
- VRAM
- 15GB
Recommended Models
Models we recommend for RTX 4070 Ti Super.
Best quality
ornith-1.0-35b
35B
21.3 tok/sQuality 79.3
Highest completed quality score at 79.3.
Frequently asked questions
Which models actually run best on the RTX 4070 Ti Super, by task, from community benchmark data.
- What is the best local model for coding on the RTX 4070 Ti Super?
- On the RTX 4070 Ti Super, ornith-1.0-35b ranks first for coding in our benchmarks (82.0/100 at ~21.3 tok/s).
- What is the best local model for agentic workflows on the RTX 4070 Ti Super?
- On the RTX 4070 Ti Super, unsloth/gemma-4-26b-a4b-it-qat ranks first for agentic workflows in our benchmarks (86.3/100 at ~48.4 tok/s). lmstudio-community/lfm2.5-2.6b is faster (~132.7 tok/s) and still scores well (81.6/100) — a good pick if you'd rather trade a little quality for speed.
Benchmark Results
Completed quality-ranked benchmark results for NVIDIA GeForce RTX 4070 Ti SUPER.