L4 rental price: from $0.44/hr today

L4 offers: 14 configurations from 10 providers

On-demand and secure-cloud rates are capacity the provider runs, with no reservation. Spot and community capacity can be interrupted. A marketplace host is one independent owner's server listed on a marketplace. Prices are per GPU per hour, before storage and data transfer. Every row shows the date it was checked.

L4 price history and range

L4 prices by provider and billing type

Each provider's cheapest rate in each billing type, per GPU-hour. The provider name opens its L4 page with node sizes, fees and its own history.

L4 hardware specs

Manufacturer datasheet figures for the L4. Source: www.nvidia.com.

LLM memory estimates for this GPU

These models have an estimated inference footprint within 24 GB at one or more precisions. The scenario uses 4,096 tokens, batch 1, a 16-bit KV cache and 20% runtime headroom. A memory fit does not establish speed or software compatibility.

Models that need more than one L4

• Qwen2.5 72B at 16-bit needs about 176 GB with the same context and headroom, so at least 8 cards. The cheapest L4 node with a published size that holds it: 8× at $13.35/hr (AWS, $1.67 per GPU-hour). At 8 or 4 bit it needs less; the model page recalculates.
• DeepSeek R1 Distill Llama 70B at 16-bit needs about 171 GB with the same context and headroom, so at least 8 cards. The cheapest L4 node with a published size that holds it: 8× at $13.35/hr (AWS, $1.67 per GPU-hour). At 8 or 4 bit it needs less; the model page recalculates.
• Mixtral 8x7B v0.1 at 16-bit needs about 113 GB with the same context and headroom, so at least 5 cards. The cheapest L4 node with a published size that holds it: 8× at $13.35/hr (AWS, $1.67 per GPU-hour). At 8 or 4 bit it needs less; the model page recalculates.

Compare model memory requirements or change context and memory assumptions on a model's page.

When to choose the L4, and what to pick instead

Start from memory: your model, its context and your batch must fit in 24 GB (the model-fit table above estimates it). Then the L4 is the right card unless one of these fits your job better.

• Pick the A100 (40 GB, from $0.89/hr) when the model or its cache does not fit in 24 GB.
• Pick the A30 (24 GB, from $0.35/hr) when finishing sooner is worth paying more: it has 1.4 times the L4's 16-bit compute.

Our workload guides recommend the L4 for self-hosted AI agents, computer vision, text embeddings, Jupyter notebooks and speech recognition. Each compares it with the other cards that suit that job, at today's prices.

Rent or buy the L4

We have no confirmed L4 purchase price from the stores we check; renting starts at $0.44 per GPU-hour. A seller quote entered in the calculator gives the break-even.

Compare L4 purchase prices and quote availability, then enter your usage and electricity costs in the rent-versus-buy calculator. Purchase listings have their own variants, stock status and update dates. Compare two GPUs.

L4 questions

How much does it cost to rent a L4?

The cheapest L4 rental we have is $0.44 per GPU-hour on Jarvislabs (on-demand), checked 13 October 2026. The median of each provider's cheapest on-demand rate is $0.70 across 6 providers.

How much VRAM does a L4 have?

24 GB.

Where is the L4 cheapest right now?

Jarvislabs has the cheapest checked on-demand rate today at $0.44 per GPU-hour; interruptible spot or community capacity starts at $0.10 (AWS).

GPUs near the L4

• A3024 GB$0.35/hrcheapest on-demand
• RTX 409024 GB$0.35/hrcheapest on-demand
• Quadro RTX 600024 GB$0.69/hrcheapest on-demand
• RTX A500024 GB$0.27/hrcheapest on-demand
• Tesla T416 GB$0.35/hrcheapest on-demand

Related

All 24 GB+ GPUs · GPUs under $1/hr · Price movers this week · Jarvislabs review · L4 vs L40S · A10 vs L4 · A30 vs L4 · Cloud GPU for self-hosted AI agents · Best Cloud GPU for Computer Vision