NVIDIA L40S vs NVIDIA V100 32GB for local LLMs
2 reports on the NVIDIA L40S and 28 on the NVIDIA V100 32GB
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 about the same on both (864 GB/s on the NVIDIA L40S, 900 on the NVIDIA V100 32GB). 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 V100 32GB
- Memory
- 32GB
- Memory bandwidth
- 900 GB/s
- FP16 compute
- 125 TFLOPS
- Reports
- 28
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 V100 32GB |
|---|---|---|
| Qwen3.8 27B | 17.6 t/sQ8_0 | 22.6 t/sQ6_K |
| Qwen3.8 125B · 6B active | 80.1 t/sQ2_K | 19.4 t/sQ2_K, experts in RAM |
| Qwen3.6 35B · 3B active | 55.4 t/sQ8_0 | 81.9 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 | 22.6 t/sQ6_K |
| Gemma 4 26B · 4B active | 47.5 t/sQ8_0 | 57.5 t/sQ6_K |
Change the context, RAM or model in the calculator: NVIDIA L40S · NVIDIA V100 32GB
Every report on each card, with its source: NVIDIA L40S · NVIDIA V100 32GB