▸ DEVICE UNDER TEST
NVIDIA GeForce RTX 2080 Ti — 11 GB VRAM.
▸ GEFORCE RTX 2080 TI SPEC
- BRAND
- NVIDIA
- VRAM
- 11 GB GDDR6
- BANDWIDTH
- 616 GB/s
- FP16 COMPUTE
- 26.9 TFLOPS
- FP32 COMPUTE
- 13.4 TFLOPS
- CUDA CORES
- 4,352
- TENSOR CORES
- 544
- TDP
- 250 W
- ARCHITECTURE
- Turing
- MSRP
- $225
▸ AI CAPABILITY
189/ 331 models @ Q4
With 11 GB VRAM and 616 GB/s bandwidth, this GPU handles models up to 15B parameters.
Speed ≈ bandwidth / model_size × efficiency. A 7B model at Q4 runs at ~70 tok/s.
§ 01TOP MODELS FOR GEFORCE RTX 2080 TI
189 FIT · SHOWING 20| MODEL | SIZE | VRAM Q4 | TOK/S | AVG |
|---|---|---|---|---|
| StarCoder2 15B | 15B | 9.7 GB | 33 | 26.5 |
| DeepSeek R1 Distill Qwen 14B | 14.8B | 9.5 GB | 33 | 43.9 |
| DeepCoder 14B | 14.8B | 9.5 GB | 33 | 38.7 |
| Qwen2.5-Coder-14B | 14.8B | 9.5 GB | 33 | 41.3 |
| Qwen2.5-14B | 14.8B | 9.5 GB | 33 | 41.3 |
| Qwen3 14B | 14.8B | 9.5 GB | 33 | 45.7 |
| Ministral 3 14B | 14B | 9.0 GB | 35 | 25.9 |
| Phi-3-medium-14b | 14B | 9.0 GB | 35 | 33.7 |
| phi-4 14B | 14B | 9.0 GB | 35 | 33.7 |
| Phi-4-reasoning 14B | 14B | 9.0 GB | 35 | 33.7 |
| Phi-4-multimodal 14B | 14B | 9.0 GB | 35 | 42.0 |
| Qwen 1.5 14B | 14B | 9.0 GB | 35 | 41.3 |
| LLaVA-1.5 13B | 13.1B | 8.5 GB | 38 | 52.1 |
| Baichuan2 13B | 13B | 8.4 GB | 38 | 23.6 |
| Llama 2 13B | 13B | 8.4 GB | 38 | 19.7 |
| CodeLlama 13B | 13B | 8.4 GB | 38 | 19.7 |
| Vicuna 13B | 13B | 8.4 GB | 38 | 11.8 |
| LLaMA 1 13B | 13B | 8.4 GB | 38 | 32.9 |
| OPT 13B | 13B | 8.4 GB | 38 | 35.8 |
| Orca 2 13B | 13B | 8.4 GB | 38 | 25.4 |