NVIDIA RTX 2080 Ti GPU: Specs, VRAM, Price & Benchmarks (2026)
The RTX 2080 Ti is a real GPU (launched 2018), 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 2080 Ti have?
The RTX 2080 Ti has 11GB GDDR6, with 616 GB/s of peak memory bandwidth.
RTX 2080 Ti 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 2080 Ti run?
Popular open models from small to frontier scale, with the memory each needs and how many RTX 2080 Ti cards (11GB GDDR6 each) that takes.
| Model | As published | FP8 | INT4 |
|---|---|---|---|
| Qwen/Qwen3-8B 8.2B | BF16: not supported | FP8: not supported | INT4: ~4.6 GB, 1 GPU |
| Qwen/Qwen2.5-14B-Instruct 14.8B | BF16: not supported | FP8: not supported | INT4: ~8.3 GB, 1 GPU |
| Qwen/Qwen3-32B 32.8B | BF16: not supported | FP8: not supported | INT4: ~18.3 GB, 2 GPUs |
| Qwen/Qwen-72B 72.3B | BF16: not supported | FP8: not supported | INT4: ~40.4 GB, 4 GPUs |
| MiniMaxAI/MiniMax-M2.7 228.7B | FP8: not supported | – | INT4: ~128 GB, 12 GPUs |
| deepseek-ai/DeepSeek-R1 684.5B | FP8: not supported | – | INT4: ~383 GB, 35 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 2080 Ti VRAM calculator.
RTX 2080 Ti specs
| Architecture | launched 2018 |
| VRAM | 11GB GDDR6 |
| Memory bandwidth | 616 GB/s |
| FP16 / BF16 tensor throughput | 107.6 TFLOPS (peak, dense) |
| Interconnect | NVLink, 2-way, 100 GB/s bidirectional |
| TDP | 250W (260W Founders Edition) |
| 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, NVLink vs PCIe
Good for
11GB and 616 GB/s with working tensor cores at a low hourly rate. A 7-8B model fits at INT8 or INT4 with context, and a pair over NVLink pools 22GB.
Not good for
Turing has no BF16 and no FP8, so FP16 is the only half-precision path, and 11GB rules out a 7B model at FP16 with any real context. No ECC.
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.
