Compact single-slot professional GPU for entry-level AI and visualization.
Weekly median price per GPU per hour
By provider shows one card per company, placed where its best offer ranked. By configuration lists every offer.
What you can rent comes first: in stock, then waitlist, then not reported, then out of stock. Priced offers rank ahead of quote-only, and on-demand ahead of other billing types.
Within a group, five factors set the order:
We match the provider, its country, GPU model, form factor, billing type, availability and instance name. Matching is partial and case-insensitive. Everyday words work too, so "interruptible" finds spot and "sold out" finds out of stock.
USA
4 configs
1x-8x
USA
58 configs
1x-10x
USA
1 config
1x
USA
3 configs
1x-4x
France
8 configs
1x-10x
UAE
6 configs
1x-10x
Singapore
3 configs
1x-4x
UK
2 configs
1x
USA
1 config
1x
USA
8 configs
1x
USA
4 configs
8x
Japan
1 config
1x
No providers match .
Heads up: A provider's own page may quote a different figure, for example on tax, region or a promotion. A monthly-only plan shows a derived hourly rate. Verify before provisioning. More on how we price.
One A4000 has 16 GB of VRAM. In practice, that's enough memory for roughly 8B parameters at 4-bit or 2B at 16-bit, assuming a 32K context. Below are some open-weight LLMs, with the estimated memory and GPUs each one needs.
| Model | Memory (INT4 / FP4) | A4000s needed | Cost /hr | Cost /mo |
|---|---|---|---|---|
Qwen3.8-27B
27B
|
19 GB
|
2
|
$0.38
|
$274
|
Gemma 4 31B
30.7B
|
24 GB
|
2
|
$0.38
|
$274
|
GPT-OSS-120B
117B · 5.1B active
|
68 GB
|
6
|
$1.14
|
$821
|
GLM-5.3-Flash
320B · 18B active
|
178 GB
|
13
|
–
|
–
|
MiniMax-M3
428B · 23B active
|
241 GB
|
17
|
–
|
–
|
DeepSeek V4.1 Flash
552B · 16B active
|
306 GB
|
22
|
–
|
–
|
Kimi K3
2.8T · 104B active
|
1,545 GB
|
108
|
–
|
–
|
Estimates based on the median on-demand rate. Memory is weights plus FP16/BF16 KV cache at 32K context per request. GPU counts assume 90% of advertised VRAM is usable. No guarantee of runtime support, usable performance, or that a matching quantized build exists. How we estimate costs.
Nvidia A4000 · Per GPU
| Compute · dense | |
|---|---|
| FP16 / BF16 | 76.7 TFLOPS 153.4 with sparsity |
| FP32 | 19.2 TFLOPS |
| Precision support | FP16BF16TF32FP32INT4INT8 |
| Memory | |
|---|---|
| Capacity | 16 GB GDDR6 |
| Bandwidth | 448 GB/s |
| Bus width | 256-bit |
| ECC | Yes |
| Silicon | |
|---|---|
| Architecture | Ampere |
| Process | Samsung 8N |
| Transistors | 17.4 billion |
| Shader cores | 6,144 CUDA cores |
| Matrix cores | 192 Tensor cores |
| Compute units | 48 SMs |
| Fabric and host | |
|---|---|
| Host interface | PCIe 4.0 x16 |
| Power | |
|---|---|
| Board power | 140 W |
| Cooling | Active |
Source: official Nvidia A4000 datasheet.
As of September 13, 2026, the median on-demand price is $0.19 per GPU per hour across 10 providers.
| Billing type | Configs | Median /GPU/hr | Cheapest |
|---|---|---|---|
On-demand | 48 | $0.19 | $0.07 (in stock, Vast.ai) |
Reserved | 37 | $0.18 | $0.05 (3 mo, in stock, Vast.ai) |
Spot | 14 | $0.06 (in stock, Vast.ai) |
No median for spot: we only show this when at least 3 providers list the GPU on that billing type. 1 provider also quotes the A4000 on a custom contract, priced per deal.
At 720 hours per month, one A4000 costs an estimated $137 at the median on-demand price. Cheapest verified in stock: $50 per month on-demand, $36 reserved (3 mo), $43 spot.
GetDeploying currently tracks A4000 configs from 13 providers. The cheapest verified in-stock on-demand configs come from Vast.ai, GPU.ai, Spheron and Sesterce. See the full price comparison above for every provider and config.
As of September 13, 2026, the median on-demand price has been flat over the past 90 days, at about $0.19 per GPU per hour.
One A4000 runs models up to roughly 8B parameters at 4-bit quantization or 2B at 16-bit, assuming a 32K context. Larger models run across multiple GPUs: the model table above shows the estimated memory and GPU count for popular open-weight LLMs.
16GB GDDR6, compact single-slot professional GPU. Low power consumption. Suitable for entry-level AI development and visualization.
No NVLink. 16GB VRAM limits model sizes. For dedicated cloud AI inference, the L4 offers better throughput at lower cost.
Last updated
