Mid-range workstation GPU for 3D and AI development.
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.
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 A4500 has 20 GB of VRAM. In practice, that's enough memory for roughly 15B parameters at 4-bit or 4B 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) | A4500s needed | Cost /hr | Cost /mo |
|---|---|---|---|---|
Qwen3.8-27B
27B
|
19 GB
|
2
|
–
|
–
|
Gemma 4 31B
30.7B
|
24 GB
|
2
|
–
|
–
|
GPT-OSS-120B
117B · 5.1B active
|
68 GB
|
4
|
–
|
–
|
GLM-5.3-Flash
320B · 18B active
|
178 GB
|
10
|
–
|
–
|
MiniMax-M3
428B · 23B active
|
241 GB
|
14
|
–
|
–
|
DeepSeek V4.1 Flash
552B · 16B active
|
306 GB
|
17
|
–
|
–
|
Kimi K3
2.8T · 104B active
|
1,545 GB
|
86
|
–
|
–
|
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 A4500 · Per GPU
| Compute · dense | |
|---|---|
| FP16 / BF16 | 94.6 TFLOPS 189.2 with sparsity |
| FP32 | 23.7 TFLOPS |
| Precision support | FP16BF16TF32FP32INT4INT8 |
| Memory | |
|---|---|
| Capacity | 20 GB GDDR6 |
| Bandwidth | 640 GB/s |
| Bus width | 320-bit |
| ECC | Yes |
| Silicon | |
|---|---|
| Architecture | Ampere |
| Process | Samsung 8N |
| Transistors | 28.3 billion |
| Shader cores | 7,168 CUDA cores |
| Matrix cores | 224 Tensor cores |
| Compute units | 56 SMs |
| Fabric and host | |
|---|---|
| Host interface | PCIe 4.0 x16 |
| Power | |
|---|---|
| Board power | 200 W |
| Cooling | Active |
Source: official Nvidia A4500 datasheet.
As of September 16, 2026, we track 4 configs from 2 providers. Prices are per GPU per hour.
| Billing type | Configs | Median /GPU/hr | Cheapest |
|---|---|---|---|
On-demand | 3 | $0.19 (in stock, Runpod) |
|
Reserved | 1 | On request |
No median for on-demand: we only show this when at least 3 providers list the GPU on that billing type.
The cheapest verified in-stock on-demand A4500 tracked by GetDeploying is $0.19 per GPU per hour from Runpod.
The cheapest verified in-stock estimate is $137 per month on-demand.
GetDeploying currently tracks A4500 configs from 2 providers. Runpod has verified in-stock on-demand configs. See the full price comparison above for every provider and config.
One A4500 runs models up to roughly 15B parameters at 4-bit quantization or 4B 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.
20GB GDDR6, professional workstation GPU with Ampere Tensor Cores. Suitable for mid-range AI development and CAD work.
Nvidia L4
24 GB GDDR6 · 53% less bandwidth than the A4500
Nvidia A10
24 GB GDDR6 · data center card
Nvidia A5000
24 GB GDDR6 · 20% more bandwidth than the A4500
Last updated
