NVIDIA RTX 4080 Super vs NVIDIA RTX 5070 Ti for local LLMs
7 reports on the NVIDIA RTX 4080 Super and 50 on the NVIDIA RTX 5070 Ti
Which is faster for local LLMs?
Nobody has reported the same model at the same quant on both cards yet, so there's no measured head-to-head. Memory bandwidth, which caps how fast a card can write, is 22% higher on the NVIDIA RTX 5070 Ti (736 GB/s on the NVIDIA RTX 4080 Super, 896 on the NVIDIA RTX 5070 Ti). The estimates below compare them on the models people run most.
- Memory
- 16GB
- Memory bandwidth
- 736 GB/s
- FP16 compute
- 209 TFLOPS
- Reports
- 7
- Memory
- 16GB
- Memory bandwidth
- 896 GB/s
- FP16 compute
- 176 TFLOPS
- Reports
- 50
Estimated by the calculator
The quant the calculator recommends for each card and its estimated speed at a 32,768-token context with 32 GB of system RAM, from memory bandwidth and the model's shape.
| Model | NVIDIA RTX 4080 Super | NVIDIA RTX 5070 Ti |
|---|---|---|
| Qwen3.8 27B | 48.0 t/sQ2_K | 58.4 t/sQ2_K |
| Qwen3.8 125B · 6B active | doesn't fit at these settings | doesn't fit at these settings |
| Qwen3.6 35B · 3B active | 158.7 t/sQ2_K | 193.2 t/sQ2_K |
| DeepSeek V4 Flash 284B · 13B active | doesn't fit at these settings | doesn't fit at these settings |
| Qwen3.6 27B | 48.0 t/sQ2_K | 58.4 t/sQ2_K |
| Gemma 4 26B · 4B active | 107.0 t/sQ3_K_S | 130.3 t/sQ3_K_S |
Change the context, RAM or model in the calculator: NVIDIA RTX 4080 Super · NVIDIA RTX 5070 Ti
Every report on each card, with its source: NVIDIA RTX 4080 Super · NVIDIA RTX 5070 Ti