Best GPUs to rent for LLM inference

For LLM inference, VRAM decides which model fits and price-per-hour decides your cost per token. A 24GB RTX 4090 serves 7B–14B models (or 4-bit 34B) at the best tokens-per-dollar on the market. Models around 70B need ~48GB in 4-bit — one L40S/RTX 6000 Ada or two 24GB cards. Latency-critical or high-batch production workloads still favor H100/A100 with HBM bandwidth.

Prices below are live minimum / median USD per hour on the GPUniq marketplace, as of 2026-07-21 00:37 UTC. Refreshed every 5 minutes.

#GPUVRAMMin $/hrMedian $/hrAvailableWhy this card
1RTX 409024GB GDDR6X$0.30$0.561613Best tokens-per-dollar for 7B–14B (and 4-bit 34B) models; huge availability.
2RTX 509032GB GDDR7$0.44$0.70278032GB GDDR7 — fits bigger quantized models than the 4090 with a healthy speed bump.
3RTX 309024GB GDDR6X$0.15$0.221128Same 24GB as the 4090 at a steep discount — the value pick for steady-state serving.
4L40S48GB GDDR6$0.70$1.216848GB in one card — 70B models in 4-bit without multi-GPU complexity.
5A10040–80GB HBM2e$0.80$1.31199HBM bandwidth for high-batch serving; 80GB fits 70B in 8-bit.
6H10080GB HBM3$2.61$3.4284Lowest latency and highest throughput when SLAs matter more than $/hr.

Source: GPUniq live marketplace analytics (2026-07-21 00:37 UTC). Each linked page shows price history for 24h/7d/30d/365d.

Frequently asked questions

What GPU do I need to run a 70B model?

In 4-bit quantization a 70B model needs roughly 40–48GB of VRAM: one L40S / RTX 6000 Ada (48GB), or two 24GB cards (2× RTX 4090/3090) with tensor parallelism. For 8-bit you need ~80GB — an A100/H100 80GB or H200.

What is the cheapest way to serve a 7B–13B model?

A single RTX 3090 or RTX 4090 (24GB) running vLLM covers 7B–13B in fp16 and up to ~34B in 4-bit. On GPUniq these cards rent from well under a dollar per hour — check the live minimum price in the table above, which updates every 5 minutes.

Do I need an H100 for inference?

Only when latency SLAs, very large batch sizes, or 100B+ models demand HBM bandwidth. For most self-hosted assistants and batch pipelines, consumer 24GB cards deliver several times more tokens per dollar.

More GPU guides