NVIDIA RTX 5060 GPU: Specs, VRAM, Price & Benchmarks (2026)
The RTX 5060 is a real GPU (launched 2025), but no provider on Aquanode is listing it for rental right now, so there is no live hourly price to quote. Availability changes as providers add and retire hardware; the specs, VRAM and price context below still apply.
How much VRAM does the RTX 5060 have?
The RTX 5060 has 8GB GDDR7, with 448 GB/s of peak memory bandwidth.
RTX 5060 VRAM calculator: check which models fit in its memory at each precision.
All models that fit in 8 GB: the open models whose weights and overhead fit, at native, FP8 and INT4 precision.
What can the RTX 5060 run?
Popular open models from small to frontier scale, with the memory each needs and how many RTX 5060 cards (8GB GDDR7 each) that takes.
| Model | As published | FP8 | INT4 |
|---|---|---|---|
| Qwen/Qwen3-8B 8.2B | BF16: ~18.3 GB, 3 GPUs | FP8: ~9.2 GB, 2 GPUs | INT4: ~4.6 GB, 1 GPU |
| Qwen/Qwen2.5-14B-Instruct 14.8B | BF16: ~33 GB, 5 GPUs | FP8: ~16.5 GB, 3 GPUs | INT4: ~8.3 GB, 2 GPUs |
| Qwen/Qwen3-32B 32.8B | BF16: ~73.2 GB, 10 GPUs | FP8: ~36.6 GB, 5 GPUs | INT4: ~18.3 GB, 3 GPUs |
| Qwen/Qwen-72B 72.3B | BF16: ~162 GB, 21 GPUs | FP8: ~80.8 GB, 11 GPUs | INT4: ~40.4 GB, 6 GPUs |
| MiniMaxAI/MiniMax-M2.7 228.7B | FP8: ~256 GB, 32 GPUs | – | INT4: ~128 GB, 16 GPUs |
| deepseek-ai/DeepSeek-R1 684.5B | FP8: ~765 GB, 96 GPUs | – | INT4: ~383 GB, 48 GPUs |
Estimates: weights at the stated precision plus a flat 20% for KV cache and overhead, at a moderate context length. A dash means the precision is not offered for that model (it is already published at that size). INT4 needs a published quantized checkpoint. Open any model for a per-GPU breakdown, or use the RTX 5060 VRAM calculator.
RTX 5060 specs
| Architecture | launched 2025 |
| VRAM | 8GB GDDR7 |
| Memory bandwidth | 448 GB/s |
| TDP | 145W |
| Form factor | PCIe |
Specs sourced from the vendor's public product page. See the source.
GPU Glossary: What is VRAM?, Tensor Cores, CUDA Cores, TFLOPS
Good for
GDDR7 gives this 8GB card 448 GB/s, 65% more than the RTX 4060, plus fifth-generation tensor cores with FP4. Fast for 7-8B models at INT4.
Not good for
Still 8GB: an 8B model at FP16 does not fit and big contexts squeeze INT4 models. No NVLink, no ECC.
RTX 5060 price by region
Related guides
Other models in the same generation. The full list is in the GPU index.
Get notified when the price drops
GPU supply moves hourly. Tell us what you're waiting for and we'll email you when a matching offer appears across any provider we track.