NVIDIA A4000 - 16GB usable
Specifications
| Brand | NVIDIA |
|---|---|
| Model | A4000 |
| Usable VRAM | 16GB |
| Architecture | Ampere |
| CUDA / Stream Processors | 6,144 |
| Memory Bandwidth | 448 GB/s |
| TDP | 140W |
| FP32 TFLOPS | 19.2 |
Current Offers
Used from £798
Prices last updated:
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 Aug 2026 · Shipping may be extra
- eBay £798 mid-range
About these prices
Each line is the lowest offer we tracked from that retailer at weekly snapshots, ending at today's offer. A dotted stretch means no offer was recorded in between. The condition can vary between snapshots (new, used, or unrecorded for older ones). eBay prices exclude shipping.
Weekly offers table
| Date | eBay |
|---|---|
| Today, Nov 12, 2026 | £797.79 |
| Nov 6, 2026 | £785.00 |
| Oct 30, 2026 | £799.99 |
| Oct 23, 2026 | £825.00 |
| Oct 9, 2026 | £825.00 |
| Oct 2, 2026 | £900.00 |
| Sep 25, 2026 | £900.00 |
| Sep 18, 2026 | £900.00 |
| Sep 11, 2026 | £834.32 |
| Sep 4, 2026 | £771.70 |
| Sep 1, 2026 | £781.90 |
| Aug 28, 2026 | £781.90 |
| Aug 21, 2026 | £750.28 |
For AI / LLM Use
Good for 14B models. 30B requires aggressive quantization.
What Models Can It Run?
- 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: ~34 tokens/sec
Prefill: ~343 tokens/sec
Recommended Quantisations
- Q4_K_M for 14B models
- Q6_K for 7B-8B models
- Q8 for 7B if VRAM allows
Pros & Cons
Pros
- Only 140W TDP: power efficient
- Ampere architecture: broad CUDA software support
- Workstation card with display outputs and active cooling
Cons
- 16GB usable VRAM: may need quantization for 30B+ models
- Moderate memory bandwidth: not the fastest for inference
Community Verdict
No community reviews yet for the A4000. Know a good review? Let us know.