Cheapest on-demand NVIDIA L40 (48 GB) on 2026-10-13 17:21 UTC: $0.820 per GPU-hour on RunPod. Prices from 1 provider, checked every hour.
What can I run on it? Open the calculator →| Provider | Per GPU-hour | 1 GPU, per month | Rent |
|---|---|---|---|
| RunPod | $0.820 | $598.60 | Rent on RunPod (opens in a new tab) → |
On-demand, per GPU, checked every hour. Monthly = 730 hours. Some links are affiliate links: StudioTV may earn a commission, at no extra cost to you.
Loading the daily history…
With 4-bit weights and an 8K-token context, a single NVIDIA L40 runs: Ornith 1.5 35B-A3B, Qwen3.5 35B-A3B, Qwen3.6 35B-A3B, MiniCPM-V-4.7 35B-A3B, Agnes-3.0-Flash, DeepSeek R1 Distill Qwen 32B, Qwen2.5 32B, Qwen2.5-Coder 32B, Qwen3 32B, Nemotron 3 Nano 30B-A3B, Nemotron 3.5 Lightning 30B-A3B, Gemma 4 31B, Qwen3 30B-A3B, Qwen3-Coder 30B-A3B, JEV 27B VL, Qwen3.6 27B, Qwen3.5 27B, Qwen3.8 27B, Clef, Gemma 4 26B-A4B, Mistral Small 3.1 24B, Mistral Small 3.2 24B, LFM2.5 24B-A2B, LFM2 24B-A2B, gpt-oss 20B, DeepSeek R1 Distill Qwen 14B, Qwen2.5-Coder 14B, Qwen2.5 14B, Qwen3 14B, Mistral Nemo, Mellum2.1 12B-A2.5B, Gemma 4 12B, Humanizer, Ornith 1.5 9B, Qwen3.5 9B, Clef Flash, LFM2.5 8B-A1B, DeepSeek R1 Qwen3 8B, Qwen3 8B, DeepSeek R1 Distill Llama 8B, Llama 3.1 8B, Ministral 8B, Gemma 4 E4B, DeepSeek R1 Distill Qwen 7B, Qwen2.5 7B, Qwen2.5-Coder 7B, Mistral 7B v0.3, Youtu-Parsing-Omni, Gemma 4 E2B, Qwen3.5 4B, LightOnOCR-3 4B, Spark-X2.5 4B, Qwen3 4B, Nemotron 3 Nano 4B, D1 3B, Qwen2.5 3B, Qwen2.5-Coder 3B.
On 2026-10-13, the cheapest on-demand NVIDIA L40 costs $0.820 per GPU-hour on RunPod. An 8-GPU server costs about $6.56 per hour, and one GPU running all month about $598.60.
RunPod at $0.820 per hour on 2026-10-13. Marketplace prices (Vast.ai) depend on the host and move within the day; the history on this page shows how they evolve.
With 4-bit weights and an 8K-token context: Ornith 1.5 35B-A3B, Qwen3.5 35B-A3B, Qwen3.6 35B-A3B, MiniCPM-V-4.7 35B-A3B, Agnes-3.0-Flash, DeepSeek R1 Distill Qwen 32B, Qwen2.5 32B, Qwen2.5-Coder 32B, Qwen3 32B, Nemotron 3 Nano 30B-A3B, Nemotron 3.5 Lightning 30B-A3B, Gemma 4 31B, Qwen3 30B-A3B, Qwen3-Coder 30B-A3B, JEV 27B VL, Qwen3.6 27B, Qwen3.5 27B, Qwen3.8 27B, Clef, Gemma 4 26B-A4B, Mistral Small 3.1 24B, Mistral Small 3.2 24B, LFM2.5 24B-A2B, LFM2 24B-A2B, gpt-oss 20B, DeepSeek R1 Distill Qwen 14B, Qwen2.5-Coder 14B, Qwen2.5 14B, Qwen3 14B, Mistral Nemo, Mellum2.1 12B-A2.5B, Gemma 4 12B, Humanizer, Ornith 1.5 9B, Qwen3.5 9B, Clef Flash, LFM2.5 8B-A1B, DeepSeek R1 Qwen3 8B, Qwen3 8B, DeepSeek R1 Distill Llama 8B, Llama 3.1 8B, Ministral 8B, Gemma 4 E4B, DeepSeek R1 Distill Qwen 7B, Qwen2.5 7B, Qwen2.5-Coder 7B, Mistral 7B v0.3, Youtu-Parsing-Omni, Gemma 4 E2B, Qwen3.5 4B, LightOnOCR-3 4B, Spark-X2.5 4B, Qwen3 4B, Nemotron 3 Nano 4B, D1 3B, Qwen2.5 3B, Qwen2.5-Coder 3B. Larger models need several GPUs; the LLM VRAM calculator sizes them.
NVIDIA B300 / GB300 · NVIDIA B200 (HGX) · NVIDIA H200 · NVIDIA H100 NVL · NVIDIA H100 · NVIDIA H100 PCIe · NVIDIA A100 80GB · NVIDIA A100 40GB · NVIDIA L40S · NVIDIA L4 · NVIDIA A40 · AMD MI355X / MI350X · AMD MI300X · RTX PRO 6000 Blackwell · RTX 6000 Ada · RTX PRO 4500 Blackwell · RTX PRO 4000 Blackwell · RTX 4000 Ada · RTX 2000 Ada · RTX A6000 · RTX A5000 · RTX A4500 · RTX A4000 · GeForce RTX 5090 · GeForce RTX 4090 · GeForce RTX 3090 Ti · GeForce RTX 3090 · GeForce RTX 5080