NVIDIA L40S vs NVIDIA Tesla P40 24GB for local LLMs
2 reports on the NVIDIA L40S and 11 on the NVIDIA Tesla P40 24GB
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 2.5x higher on the NVIDIA L40S (864 GB/s on the NVIDIA L40S, 346 on the NVIDIA Tesla P40 24GB). The estimates below compare them on the models people run most.
NVIDIA L40S
- Memory
- 48GB
- Memory bandwidth
- 864 GB/s
- FP16 compute
- 362.1 TFLOPS
- Reports
- 2
NVIDIA Tesla P40 24GB
- Memory
- 24GB
- Memory bandwidth
- 346 GB/s
- FP16 compute
- 12 TFLOPS
- Reports
- 11
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 L40S | NVIDIA Tesla P40 24GB |
|---|---|---|
| Qwen3.8 27B | 17.6 t/sQ8_0 | 12.5 t/sQ4_K_M |
| Qwen3.8 125B · 6B active | 80.1 t/sQ2_K | 16.9 t/sQ2_K, experts in RAM |
| Qwen3.6 35B · 3B active | 55.4 t/sQ8_0 | 44.4 t/sQ4_K_S |
| DeepSeek V4 Flash 284B · 13B active | doesn't fit at these settings | doesn't fit at these settings |
| Qwen3.6 27B | 17.6 t/sQ8_0 | 12.5 t/sQ4_K_M |
| Gemma 4 26B · 4B active | 47.5 t/sQ8_0 | 28.2 t/sQ5_K_S |
Change the context, RAM or model in the calculator: NVIDIA L40S · NVIDIA Tesla P40 24GB
Every report on each card, with its source: NVIDIA L40S · NVIDIA Tesla P40 24GB