GPUs & Macs › NVIDIA RTX 3080 Ti
NVIDIA RTX 3080 Ti: local LLM speed
3 measured results for the NVIDIA RTX 3080 Ti.
Measured results
| Model | Generate tok/s | Prompt tok/s | Quant | Backend | Test | Source |
|---|---|---|---|---|---|---|
| Llama 3.2 1B Instruct | 313 | 14,143 | Q4_K_M | llamafile | LocalScore avg | LocalScore details |
| Llama 3.1 8B Instruct | 90.5 | 3,515 | Q4_K_M | llamafile | LocalScore avg | LocalScore details |
| Qwen2.5 14B Instruct | 46.1 | 1,793 | Q4_K_M | llamafile | LocalScore avg | LocalScore details |
What fits on the NVIDIA RTX 3080 Ti
Estimates for this chip are scaled from a measured run: Llama 3.1 8B Instruct Q4_K_M at 90.5 tok/s (llamafile, source). Fit assumes the whole model in GPU memory with ~8K context.
| Model | Best quant that fits | File | Expected tok/s |
|---|---|---|---|
| Qwen3.8-27B | UD-IQ2_XXS | 7.3 GB | 61.3 estimate |
| gemma-4-12B-it | Q6_K | 9.8 GB | 45.5 estimate |
| Qwen3.5-9B | Q8_0 | 9.5 GB | 46.7 estimate |
| Qwen3.5-4B | Q8_0 | 4.5 GB | 99.3 estimate |
| gemma-4-26B-A4B-it | UD-IQ2_M | 10.0 GB | 145 estimate |
| MiMo-V2.6-Distill-Qwen-9B | Q8_0 | 9.5 GB | 46.6 estimate |
| gemma-4-E4B-it | Q8_0 | 8.2 GB | 54.4 estimate |
| Qwen3-4B | Q8_0 | 4.3 GB | 104 estimate |
| gemma-4-31B-it | UD-IQ2_XXS | 8.5 GB | 52.2 estimate |
| gemma-4-12B-it-qat-q4_0-unquantized | UD-Q4_K_XL | 6.7 GB | 66.3 estimate |
| gemma-3-1b-it | Q8_0 | 1.1 GB | 371 estimate |
| gemma-4-E2B-it | Q8_0 | 5.0 GB | 89.6 estimate |
| DeepSeek-R1-0528-Qwen3-8B | Q8_0 | 8.7 GB | 51.1 estimate |
| Llama-3.2-3B-Instruct | Q8_0 | 3.4 GB | 130 estimate |
Similar hardware
NVIDIA RTX 5070 · NVIDIA TITAN V · NVIDIA TITAN Xp · NVIDIA RTX 3060 · NVIDIA RTX 4070 Ti · NVIDIA RTX 4070 SUPER · NVIDIA RTX 4070 · NVIDIA RTX 2080 Ti