NVIDIA L40S - 48GB usable
Specifications
| Brand | NVIDIA |
|---|---|
| Model | L40S |
| Usable VRAM | 48GB |
| Architecture | Ada |
| CUDA / Stream Processors | 18,176 |
| Memory Bandwidth | 864 GB/s |
| TDP | 350W |
| FP32 TFLOPS | 91 |
Current Offers
Used from £6540
Prices last updated:
GPUDojo is reader-supported. When you buy through links on our site, we may earn an affiliate commission.
Price History
- eBay£6540mid-range
For AI / LLM Use
Best for running 70B+ models on a single GPU. Datacenter card with no display output, may need aftermarket cooling.
What Models Can It Run?
- 70B Q4_K_M, 30B full precision
- 30B Q6_K, 70B Q2_K
- 30B Q4_K_M, 14B full precision, 70B Q2 (tight)
- 14B Q6_K, 30B Q3_K (tight)
- 14B Q4_K_M, 7B full precision
- 7B Q6_K, 14B Q3_K (tight)
- 7B Q4_K_M only
Estimated Performance
Generation: ~65 tokens/sec
Prefill: ~1625 tokens/sec
Recommended Quantisations
- Q6_K or Q8 for best quality
- Q4_K_M for larger models
- Full precision for 30B and below
Pros & Cons
Pros
- 48GB usable VRAM: handles large models
- High memory bandwidth for fast generation
- Ada architecture: broad CUDA software support
Cons
- 350W TDP: high power draw
- No display output: headless only
- May need aftermarket cooling solution
Community Verdict
No community reviews yet for the L40S. Know a good review? Let us know.