NVIDIA RTX 4070 vs NVIDIA Tesla P100 16GB for local LLMs
12 reports on the NVIDIA RTX 4070 and 15 on the NVIDIA Tesla P100 16GB
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 45% higher on the NVIDIA Tesla P100 16GB (504 GB/s on the NVIDIA RTX 4070, 732 on the NVIDIA Tesla P100 16GB). The estimates below compare them on the models people run most.
- Memory
- 12GB
- Memory bandwidth
- 504 GB/s
- FP16 compute
- 116 TFLOPS
- Reports
- 12
- Memory
- 16GB
- Memory bandwidth
- 732 GB/s
- FP16 compute
- 19 TFLOPS
- Reports
- 15
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 4070 | NVIDIA Tesla P100 16GB |
|---|---|---|
| Qwen3.8 27B | 1.7 t/sQ8_0, layers on CPU | 47.7 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 | 13.9 t/sQ6_K, experts in RAM | 157.9 t/sQ2_K |
| DeepSeek V4 Flash 284B · 13B active | doesn't fit at these settings | doesn't fit at these settings |
| Qwen3.6 27B | 1.7 t/sQ8_0, layers on CPU | 47.7 t/sQ2_K |
| Gemma 4 26B · 4B active | 82.3 t/sQ2_K | 106.4 t/sQ3_K_S |
Change the context, RAM or model in the calculator: NVIDIA RTX 4070 · NVIDIA Tesla P100 16GB
Every report on each card, with its source: NVIDIA RTX 4070 · NVIDIA Tesla P100 16GB