L4 pricing on FireVM
Every FireVM L4 offering we track, normalized to a per-GPU hourly rate and ranked against 24 providers with current L4 pricing.
The cheapest L4 we currently track is $0.269/hr on Vast.ai.
FireVM L4 rates
Hourly prices per GPU. Multi-GPU rows show the per-GPU rate, not the instance total.
| Price / GPU-hr | Type | GPUs |
|---|---|---|
| $0.582 | Reserved1 mo | 2 |
| $0.615 | Reserved1 mo | 1 |
L4 specifications
- VRAM
- 24GB
- Architecture
- Ada Lovelace
- CUDA Cores
- 7,424
- Tensor Cores
- 232
- Memory Bandwidth
- 300 GB/s
- TDP
- 72W
L4 on other providers
- Vast.ai$0.269/hr
- Google Cloud$0.318/hr
- gpu.ai$0.340/hr
- Seeweb$0.425/hr
- OpenRelay$0.430/hr
- Jarvis Labs$0.440/hr
- AtmosCompute$0.460/hr
- Runpod$0.590/hr
- UpCloud$0.637/hr
- Aquanode$0.649/hr
- AceCloud$0.662/hr
- Hugging Face$0.700/hr
- Modal$0.799/hr
- Amazon AWS$0.805/hr
- Baseten$0.850/hr
- Scaleway$0.882/hr
- Shadeform$0.950/hr
- Omega Gradient$1.00/hr
- OVHcloud$1.00/hr
- IO.NET$1.02/hr
- Sesterce$1.04/hr
- Runcrate$1.23/hr
- Hinode$1.75/hr
About FireVM
FireVM is a managed hosting company that rents single-tenant bare-metal GPU servers alongside its web hosting, VPS and dedicated server plans. GPU servers carry one to four cards (NVIDIA Tesla T4, L4, A30, L40S, RTX PRO 6000, H100 NVL and H200 NVL, plus AMD MI210) in Canada, Europe and the UK, billed per month with no hourly meter and no minimum term. Eight-GPU servers in the USA are sold by pre-order with a deposit.
Frequently Asked Questions
How much does the L4 cost on FireVM?
FireVM lists the L4 from $0.582 per GPU-hour across 2 tracked configurations. Prices are collected daily — see the table above for the current rates.
Is FireVM the cheapest place to rent the L4?
FireVM ranks #8 of 24 providers we track with current L4 pricing. The cheapest right now is Vast.ai. Price is only one factor — region availability, network, and storage costs differ between providers.
Which L4 configurations does FireVM offer?
We currently track 2 L4 offerings from FireVM, covering the GPU counts, pricing types, and regions listed in the table above. Every price is normalized to a per-GPU hourly rate so it can be compared across providers.