GPUs & Macs › NVIDIA RTX 5000 Ada Laptop
NVIDIA RTX 5000 Ada Laptop: local LLM speed
1 measured result for the NVIDIA RTX 5000 Ada Laptop.
Measured results
| Model | Generate tok/s | Prompt tok/s | Quant | Backend | Test | Source |
|---|---|---|---|---|---|---|
| Qwen2.5 14B Instruct | 16.4 | 952 | Q4_K_M | llamafile | LocalScore avg | LocalScore details |
What fits on the NVIDIA RTX 5000 Ada Laptop
Estimates for this chip are scaled from a measured run: Qwen2.5 14B Instruct Q4_K_M at 16.4 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 | 13.5 estimate |
| gemma-4-12B-it | Q8_0 | 12.7 GB | 11.6 estimate |
| Qwen3.5-9B | Q8_0 | 9.5 GB | 15.5 estimate |
| Qwen3.5-4B | Q8_0 | 4.5 GB | 32.9 estimate |
| Qwen3.6-35B-A3B | UD-IQ3_XXS | 13.2 GB | 65.1 estimate |
| gemma-4-26B-A4B-it | UD-IQ4_XS | 13.6 GB | 35.2 estimate |
| MiMo-V2.6-Distill-Qwen-9B | Q8_0 | 9.5 GB | 15.4 estimate |
| gemma-4-E4B-it | Q8_0 | 8.2 GB | 18.0 estimate |
| Muse-Glimmer-30B | UD-IQ3_XXS | 13.1 GB | 11.2 estimate |
| Qwen3-4B | Q8_0 | 4.3 GB | 34.4 estimate |
| gemma-4-31B-it | UD-IQ3_XXS | 11.8 GB | 12.4 estimate |
| gemma-4-12B-it-qat-q4_0-unquantized | UD-Q4_K_XL | 6.7 GB | 21.9 estimate |
| gemma-3-1b-it | Q8_0 | 1.1 GB | 123 estimate |
| gemma-4-E2B-it | Q8_0 | 5.0 GB | 29.7 estimate |
Similar hardware
NVIDIA RTX 3080 Laptop · NVIDIA RTX A5000 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