NVIDIA L40S vs NVIDIA RTX 5090 for local LLMs
2 reports on the NVIDIA L40S and 168 on the NVIDIA RTX 5090
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 2.1x higher on the NVIDIA RTX 5090 (864 GB/s on the NVIDIA L40S, 1,792 on the NVIDIA RTX 5090). 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 RTX 5090
- Memory
- 32GB
- Memory bandwidth
- 1,792 GB/s
- FP16 compute
- 419 TFLOPS
- Reports
- 168
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 RTX 5090 |
|---|---|---|
| Qwen3.8 27B | 17.6 t/sQ8_0 | 44.9 t/sQ6_K |
| Qwen3.8 125B · 6B active | 80.1 t/sQ2_K | 20.3 t/sQ2_K, experts in RAM |
| Qwen3.6 35B · 3B active | 55.4 t/sQ8_0 | 163.0 t/sQ5_K_M |
| 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 | 44.9 t/sQ6_K |
| Gemma 4 26B · 4B active | 47.5 t/sQ8_0 | 114.5 t/sQ6_K |
Change the context, RAM or model in the calculator: NVIDIA L40S · NVIDIA RTX 5090
Every report on each card, with its source: NVIDIA L40S · NVIDIA RTX 5090