USA
36 configs
1x-4x
Nvidia P4
Legacy inference card for lightweight, cost-sensitive deployments.
- Arch
- Pascal
- Memory
- 8 GB GDDR5
- Bandwidth
- 192 GB/s
- Released
- Q3 2016
Price history
Weekly median price per GPU per hour
Aggregating historical prices...
At a glance Updated 1 day ago
- Cheapest
- $0.65 /GPU/hr
- on-demand · not verified in stock
- Median price (current)
- --
- 90-day trend
- --
- Coverage
- 1 provider
- 36 price points
Pricing & availability
How this list works
The two views
By provider shows one card per company, placed where its best offer ranked. By configuration lists every offer.
Order
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:
- Location: datacenter proximity, blended with provider HQ.
- Price: hourly price, per GPU and in total.
- Billing type: reserved ahead of spot, spot ahead of quote-only.
- Specs: more VRAM, vCPUs and RAM.
- Provider diversity: a provider's repeat rows rank slightly lower, so one company can't take all the top spots.
Search
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.
Transparency and funding
- Ads and sponsors: Paid placements sit at the top of the list and are always labeled as sponsored content. Sponsorship never influences the organic ranking itself.
- Affiliates: Affiliate links are marked. We may earn a commission if you click them, but commissions never affect the order.
- Prices: Shown in USD, converted at daily reference rates where a provider publishes in another currency. A month means 720 hours. How we estimate costs.
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.
What can the P4 run?
One P4 has 8 GB of VRAM. Even at 4-bit, the weights of most modern AI models exceed the card's usable VRAM, and context adds KV cache on top. Below are some open-weight LLMs, with the estimated memory and GPUs each one needs.
Multi-node
| Model | Memory (INT4 / FP4) | P4s needed | Cost /hr | Cost /mo |
|---|---|---|---|---|
Qwen3.8-27B
27B
|
19 GB
|
3
|
–
|
–
|
|
Gemma 4 31B
30.7B
|
24 GB
|
4
|
–
|
–
|
GPT-OSS-120B
117B · 5.1B active
|
68 GB
|
10
|
–
|
–
|
GLM-5.3-Flash
320B · 18B active
|
178 GB
|
25
|
–
|
–
|
MiniMax-M3
428B · 23B active
|
241 GB
|
34
|
–
|
–
|
DeepSeek V4.1 Flash
552B · 16B active
|
306 GB
|
43
|
–
|
–
|
Kimi K3
2.8T · 104B active
|
1,545 GB
|
215
|
–
|
–
|
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.
Technical Specifications
Nvidia P4 · Per GPU
| Compute · dense | |
|---|---|
| INT8 | 22 TOPS |
| FP32 | 5.5 TFLOPS |
| Precision support | FP16FP32INT8 |
| Memory | |
|---|---|
| Capacity | 8 GB GDDR5 |
| Bandwidth | 192 GB/s |
| Bus width | 256-bit |
| ECC | Yes |
| Silicon | |
|---|---|
| Architecture | Pascal |
| Process | TSMC 16nm FinFET |
| Transistors | 7.2 billion |
| Shader cores | 2,560 CUDA cores |
| Compute units | 20 SMs |
| Fabric and host | |
|---|---|
| Host interface | PCIe 3.0 x16 |
| Power | |
|---|---|
| Board power | 75 W |
| Cooling | Passive |
Source: official Nvidia P4 datasheet.
Frequently Asked Questions
How much does the P4 cost per hour?
-
As of September 12, 2026, we track 36 configs from 1 provider. Prices are per GPU per hour.
Billing type Configs Cheapest On-demand
9
$0.65
Reserved
18
$0.34 (36 mo)
Spot
9
$0.12
No median for on-demand, reserved and spot: we only show this when at least 3 providers list the GPU on that billing type.
Who has the cheapest P4?
-
The lowest listed on-demand price for the P4 is $0.65 per GPU per hour from Google Cloud, though we haven't verified current stock.
Where can I rent a P4?
-
GetDeploying currently tracks P4 configs from 1 provider. See the full price comparison above for every provider and config.
How many P4 GPUs do I need?
-
More than one: even at 4-bit, the weights of most modern AI models exceed one P4's usable VRAM, and context adds KV cache on top. Larger models run across multiple GPUs: the model table above shows the estimated memory and GPU count for popular open-weight LLMs.
Why choose the P4?
-
8GB GDDR5 at very low cost. INT8 inference support. Suitable for lightweight, cost-sensitive inference deployments.
When is the P4 not a good fit?
-
Only 8GB VRAM on Pascal architecture with no Tensor Cores. Only viable for very lightweight legacy inference or basic video transcoding.
Alternatives to Nvidia P4
Last updated