GPUs & Macs › NVIDIA RTX 3080 Laptop
NVIDIA RTX 3080 Laptop: local LLM speed
3 measured results for the NVIDIA RTX 3080 Laptop.
Measured results
| Model | Generate tok/s | Prompt tok/s | Quant | Backend | Test | Source |
|---|---|---|---|---|---|---|
| Llama 3.2 1B Instruct | 157 | 7,533 | Q4_K_M | llamafile | LocalScore avg | LocalScore details |
| Llama 3.1 8B Instruct | 53.1 | 1,969 | Q4_K_M | llamafile | LocalScore avg · n=2 | LocalScore LocalScore details |
| Qwen2.5 14B Instruct | 28.2 | 858 | Q4_K_M | llamafile | LocalScore avg | LocalScore details |
What fits on the NVIDIA RTX 3080 Laptop
Estimates for this chip are scaled from a measured run: Llama 3.1 8B Instruct Q4_K_M at 53.1 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-IQ3_XXS | 10.9 GB | 23.9 estimate |
| gemma-4-12B-it | Q8_0 | 12.7 GB | 20.6 estimate |
| Qwen3.5-9B | Q8_0 | 9.5 GB | 27.4 estimate |
| Qwen3.5-4B | Q8_0 | 4.5 GB | 58.3 estimate |
| Qwen3.6-35B-A3B | UD-IQ3_XXS | 13.2 GB | 115 estimate |
| gemma-4-26B-A4B-it | UD-IQ4_XS | 13.6 GB | 62.5 estimate |
| MiMo-V2.6-Distill-Qwen-9B | Q8_0 | 9.5 GB | 27.4 estimate |
| gemma-4-E4B-it | Q8_0 | 8.2 GB | 31.9 estimate |
| Muse-Glimmer-30B | UD-IQ3_XXS | 13.1 GB | 19.9 estimate |
| Qwen3-4B | Q8_0 | 4.3 GB | 61.0 estimate |
| gemma-4-31B-it | UD-IQ3_XXS | 11.8 GB | 22.1 estimate |
| gemma-4-12B-it-qat-q4_0-unquantized | UD-Q4_K_XL | 6.7 GB | 38.9 estimate |
| gemma-3-1b-it | Q8_0 | 1.1 GB | 218 estimate |
| gemma-4-E2B-it | Q8_0 | 5.0 GB | 52.6 estimate |
Similar hardware
NVIDIA RTX A5000 Laptop · NVIDIA RTX 5000 Ada Laptop · NVIDIA RTX 4090 Laptop · NVIDIA RTX 5080 Laptop · NVIDIA RTX A4500 Laptop · NVIDIA RTX 5070 Ti Laptop · NVIDIA RTX 3500 Ada Laptop · NVIDIA RTX 5090 Laptop