GPU MODELS / RTX 4060

RTX 4060 cloud GPU pricing

3 listings across 2 providers. Cheapest published rate: $0.050/GPU/hr at Salad. Sorted by per-GPU hourly price. Every row links to the provider's own published price.

WHAT IS THE RTX 4060

The 4060 is Ada's entry card: very efficient at 115 W, but 8 GB of GDDR6 behind a narrow bus. In catalogs it is cheap dev capacity - current-enough tensor cores, not enough memory for serious model work.

MAKER
NVIDIA
ARCHITECTURE
Ada Lovelace
LAUNCHED
2023
MEMORY
8 GB GDDR6
MEMORY BANDWIDTH
272 GB/s
TENSOR COMPUTE
15.1 TFLOPS FP32; 4th-gen tensor cores
POWER DRAW
115 W
INTERCONNECT
PCIe 4.0 x8

WHAT IT IS GOOD AT

Development
Low-power Ada capacity for testing and small experiments.
7B inference
Tight - 4-bit with short context.
Anything 13B+
Not a fit - 8 GB.

WHO SHOULD NOT RENT THE RTX 4060

13B-class models and any training.
Bandwidth-bound serving.
ProviderConfigVRAMLocation$/hr$/GPU/hrSource
SaladSaladRTX 4060 × 18 GBGlobal (distributed)$0.050$0.050receipt
GPUBrazilGPUBrazilRTX 4060 × 18 GBNorth America$0.263$0.263receipt
GPUBrazilGPUBrazilRTX 4060 × 18 GBAsia-Pacific$0.263$0.263receipt

THE RTX 4060 MARKET, BY THE NUMBERS

PROVIDERS
2
CONFIGURATIONS
3
MEDIAN $/GPU/HR
$0.26
SPREAD
5.3x

2 providers publish 3 RTX 4060 configurations on the panel today. Published per-GPU hourly rates run from $0.050 (Salad) to $0.26 (GPUBrazil), a 5x spread between the cheapest and the most expensive published rate for the same chip. The median listing sits at $0.26/GPU/hr. 2 rows were reported in stock by the provider at last observation; the rest are published catalog rates. All rates are on-demand - committed-use and reserved pricing is excluded.

RTX 4060 PRICE TREND, DAILY PANEL SNAPSHOTS

Across every RTX 4060 row on the panel, the daily floor held flat at $0.050/GPU/hr over 53 days of tracking. Snapshots run daily; the full history is public in the repo.

RTX 4060 PROVIDER NOTES
Salad · 1 config · 1 region
Sets the panel floor for this model.
from $0.050/hr
GPUBrazil · 2 configs · 2 regions · 2 in stock
2 of 2 configs reported in stock at last check.
from $0.263/hr
BUYING RTX 4060: WHAT THE PANEL SAYS

At the current floor, one RTX 4060 running around the clock costs about $37 a month (730 hours of on-demand arithmetic). Compare the alternatives below before committing - the same budget often buys more than one chip class.

RTX 4060 VS THE ALTERNATIVES

RTX 4060 vs RTX 5060
Same 8 GB class, one generation newer with GDDR7 and FP4/FP8 paths. The 5060 is worth a small premium.
RTX 4060 vs RTX 3060
The 3060 is older and slower per clock but carries 12 GB - for LLM fit, the old card's memory beats the new card's speed.

Compare live rates: RTX 4060 vs RTX 5060 · RTX 4060 vs RTX 3060

RTX 4060 PRICING FAQ

What is the cheapest RTX 4060 cloud GPU right now?
The cheapest published RTX 4060 rate on the panel is $0.050 per GPU-hour at Salad (RTX 4060 x 1, Global (distributed)). Every price links to the provider's own published rate.
How much does a RTX 4060 cost per hour?
Across 2 providers tracked today, published per-GPU hourly rates for RTX 4060 run from $0.05 to $0.26, with a median of $0.26. Committed-use and reserved rates are excluded; everything shown is on-demand.
How many providers rent RTX 4060 GPUs?
2 providers publish 3 distinct RTX 4060 configurations on Compute Cafe. 2 of those rows were reported in stock by the provider's live endpoint at last observation.
Are RTX 4060 prices going up or down?
Over the 53 days Compute Cafe has tracked the panel, the RTX 4060 floor is holding flat: $0.050 to $0.050/GPU/hr (+0.0%). Daily snapshots are public in the repo, so the trend is auditable.
What does a RTX 4060 cost per month?
At the current floor of $0.050/GPU/hr, a RTX 4060 running 24/7 costs about $37 per month (730 hours of on-demand arithmetic on the cheapest published rate). Committed-use contracts can price lower; the panel tracks on-demand rates only.
Is the RTX 4060 good for LLMs?
Only 7B models at tight quantization - 8 GB is the ceiling. The 3060's 12 GB or any 16 GB card is a better LLM rental.

See also alternatives to the RTX 4060 · cheapest GPU-hour per model · inference chips · training chips · by location