NVIDIA L4 - 24GB usable
Specifications
| Brand | NVIDIA |
|---|---|
| Model | L4 |
| Usable VRAM | 24GB |
| Architecture | Ada |
| CUDA / Stream Processors | 7,424 |
| Memory Bandwidth | 300 GB/s |
| TDP | 72W |
| FP32 TFLOPS | 30 |
Current Offers
No fresh used offer today · recently £3,000 on eBay
GPUDojo is reader-supported. When you buy through links on our site, we may earn an affiliate commission.
Lowest tracked offers by retailer
UK · GBP · Weekly since Sep 2026 · Shipping may be extra
- eBay (no current offer)
About these prices
Each line is the lowest offer we tracked from that retailer at weekly snapshots, ending at today's offer. The condition can vary between snapshots (new, used, or unrecorded for older ones). eBay prices exclude shipping.
Weekly offers table
| Date | eBay |
|---|---|
| Sep 25, 2026 | £3,532.87 |
| Sep 18, 2026 | £3,478.67 |
| Sep 11, 2026 | £3,000.00 |
| Sep 4, 2026 | £3,000.00 |
| Sep 1, 2026 | £3,000.00 |
For AI / LLM Use
Solid choice for 30B models and comfortable 14B inference. Slower generation, usable but not snappy. Datacenter card with no display output, may need aftermarket cooling.
What Models Can It Run?
- 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: ~23 tokens/sec
Prefill: ~536 tokens/sec
Recommended Quantisations
- Q4_K_M recommended for 30B models
- Q6_K or Q8 for 14B and below
- Full precision for 7B
Pros & Cons
Pros
- 24GB usable VRAM: handles large models
- Only 72W TDP: power efficient
- Ada architecture: broad CUDA software support
Cons
- Moderate memory bandwidth: not the fastest for inference
- No display output: headless only
- May need aftermarket cooling solution
Community Verdict
No community reviews yet for the L4. Know a good review? Let us know.