NVIDIA · Ada Lovelace · 2022

NVIDIA RTX 4090

The people's inference GPU. On marketplaces, the best $/FLOP in the catalog.

24 GB
GDDR6X
1.01 TB/s
Mem bandwidth
165 TF
FP16 dense
330 TF
FP8 dense
450 W
TDP
$0.34 /hr
From · RunPod

24 GB runs 7B FP16 or ~32B at 4-bit. Rents for well under $0.50/hr on community marketplaces, a fraction of datacenter pricing per FLOP.

Where to rent a RTX 4090

On-demand prices per GPU-hour; marketplace rates refresh daily, list prices reviewed 2026-09. Reserved and spot run 30-70% lower. Full breakdown with the used market and rent-vs-buy math: RTX 4090 pricing.

Provider $/GPU-hr vs cheapest Notes
RunPod $0.34 cheapest Community Cloud
TensorDock $0.37 1.1× marketplace
Packet.ai $0.39 1.1× Dedicated
Vast.ai $0.43 1.3× Verified-listing rate, refreshed daily; interruptible from ~$0.20

Specifications in context

Bars scaled against the best value in the whole catalog (B200 / MI325X era).

Memory 24 GB
Memory bandwidth 1.01 TB/s
FP16 dense 165 TFLOPS
FP8 dense 330 TFLOPS
Power (TDP) 450 W
ArchitectureAda Lovelace (2022)
Memory24 GB GDDR6X, 1.01 TB/s
InterconnectPCIe Gen4
Form factorConsumer card
PartitioningNo MIG (time-slicing / vGPU only)

What fits on one RTX 4090

Weights + ~2 GB runtime overhead against 22 GB usable VRAM. Longer contexts and bigger batches need more, check the VRAM calculator.

ModelParamsHighest precision that fits
Llama 3.2 1B 1.24B FP16
Llama 3.2 3B 3.21B FP16
Llama 3.1 8B 8.03B FP16
Qwen2.5 7B 7.62B FP16
Qwen2.5 14B 14.8B 8-bit
Mistral 7B 7.25B FP16
Gemma 2 9B 9.24B 8-bit
Gemma 2 27B 27.2B 4-bit
Phi-4 14B 14.7B 8-bit
gpt-oss-20b 20.9B 4-bit

Best for

Compare

A100 80GB vs RTX 4090

The GPU that started the LLM era, now a value pick for fine-tuning and mid-size inference.

L40S vs RTX 4090

Ada silicon with 48 GB: strong FP8 compute, modest bandwidth. A favorite for image gen and mid-size LLMs.

RTX 4090 vs RTX 5090

The fastest thing you can put in a desktop: 32 GB of GDDR7 at 1.8 TB/s.

RTX 3090 vs RTX 4090

The used-market classic: 24 GB for a few hundred dollars, or pennies per hour rented.