NVIDIA RTX 3080 Ti GPU: Specs, VRAM, Price & Benchmarks (2026)
The RTX 3080 Ti is a real GPU (launched 2021), 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 3080 Ti have?
The RTX 3080 Ti has 12GB GDDR6X, with 912 GB/s of derived memory bandwidth (bus width × transfer rate; not a vendor-stated figure).
RTX 3080 Ti VRAM calculator: check which models fit in its memory at each precision.
All models that fit in 12 GB: the open models whose weights and overhead fit, at native, FP8 and INT4 precision.
What can the RTX 3080 Ti run?
Popular open models from small to frontier scale, with the memory each needs and how many RTX 3080 Ti cards (12GB GDDR6X each) that takes.
| Model | As published | FP8 | INT4 |
|---|---|---|---|
| Qwen/Qwen3-8B 8.2B | BF16: ~18.3 GB, 2 GPUs | FP8: not supported | INT4: ~4.6 GB, 1 GPU |
| Qwen/Qwen2.5-14B-Instruct 14.8B | BF16: ~33 GB, 3 GPUs | FP8: not supported | INT4: ~8.3 GB, 1 GPU |
| Qwen/Qwen3-32B 32.8B | BF16: ~73.2 GB, 7 GPUs | FP8: not supported | INT4: ~18.3 GB, 2 GPUs |
| Qwen/Qwen-72B 72.3B | BF16: ~162 GB, 14 GPUs | FP8: not supported | INT4: ~40.4 GB, 4 GPUs |
| MiniMaxAI/MiniMax-M2.7 228.7B | FP8: not supported | – | INT4: ~128 GB, 11 GPUs |
| deepseek-ai/DeepSeek-R1 684.5B | FP8: not supported | – | INT4: ~383 GB, 32 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 3080 Ti VRAM calculator.
RTX 3080 Ti specs
| Architecture | launched 2021 |
| VRAM | 12GB GDDR6X |
| Memory bandwidth | 912 GB/s |
| TDP | 350W |
| 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
12GB of GDDR6X on a 384-bit bus is the most memory a card of this class gets, enough for 7-8B models at BF16 with a usable context and for 13B models quantized to INT4. Ampere keeps BF16 tensor support.
Not good for
No FP8 tensor cores, so FP8 serving is off the table, and 12GB stops short of any 30B-class model even at INT4. 350W is a lot of heat for a 12GB card.
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.
