Fastest
qwen3.8-flash-next-iq2_xs
Unknown
80.4 tok/s
Highest token generation speed at 80.4 tok/s.
Hardware Benchmarks
Best Local LLM Performance for RTX 4070 Super
Compare RTX 4070 Super benchmark results and see which models actually earn the best completed quality scores.
Hardware Overview
GPU-specific specifications for local LLM planning.
- VRAM
- 12GB
Recommended Models
Models we recommend for RTX 4070 Super.
Best quality
Qwen3.6-35B-A3B
35B
43.9 tok/sQuality 79.9
Highest completed quality score at 79.9.
Frequently asked questions
Which models actually run best on the RTX 4070 Super, by task, from community benchmark data.
- What is the best local model for coding on the RTX 4070 Super?
- On the RTX 4070 Super, Qwen3.8-27B-LowGPU ranks first for coding in our benchmarks (76.2/100 at ~33.5 tok/s).
- What is the best local model for agentic workflows on the RTX 4070 Super?
- On the RTX 4070 Super, Qwen3.8-27B-LowGPU ranks first for agentic workflows in our benchmarks (76.5/100 at ~33.5 tok/s).
Benchmark Results
Completed quality-ranked benchmark results for NVIDIA GeForce RTX 4070 SUPER.