GPUs & Macs › NVIDIA RTX 4090 Laptop
NVIDIA RTX 4090 Laptop: local LLM speed
1 measured result for the NVIDIA RTX 4090 Laptop.
Measured results
| Model | Generate tok/s | Prompt tok/s | Quant | Backend | Test | Source |
|---|---|---|---|---|---|---|
| Llama 3.2 1B Instruct | 207 | 11,965 | Q4_K_M | llamafile | LocalScore avg | LocalScore details |
What fits on the NVIDIA RTX 4090 Laptop
No measured run yet; estimates use spec bandwidth × 0.66 (typical efficiency for NVIDIA). 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 | 34.6 estimate |
| gemma-4-12B-it | Q8_0 | 12.7 GB | 29.8 estimate |
| Qwen3.5-9B | Q8_0 | 9.5 GB | 39.7 estimate |
| Qwen3.5-4B | Q8_0 | 4.5 GB | 84.3 estimate |
| Qwen3.6-35B-A3B | UD-IQ3_XXS | 13.2 GB | 167 estimate |
| gemma-4-26B-A4B-it | UD-IQ4_XS | 13.6 GB | 90.4 estimate |
| MiMo-V2.6-Distill-Qwen-9B | Q8_0 | 9.5 GB | 39.6 estimate |
| gemma-4-E4B-it | Q8_0 | 8.2 GB | 46.1 estimate |
| Muse-Glimmer-30B | UD-IQ3_XXS | 13.1 GB | 28.8 estimate |
| Qwen3-4B | Q8_0 | 4.3 GB | 88.3 estimate |
| gemma-4-31B-it | UD-IQ3_XXS | 11.8 GB | 31.9 estimate |
| gemma-4-12B-it-qat-q4_0-unquantized | UD-Q4_K_XL | 6.7 GB | 56.3 estimate |
| gemma-3-1b-it | Q8_0 | 1.1 GB | 315 estimate |
| gemma-4-E2B-it | Q8_0 | 5.0 GB | 76.1 estimate |
Similar hardware
NVIDIA RTX 3080 Laptop · NVIDIA RTX A5000 Laptop · NVIDIA RTX 5000 Ada Laptop · NVIDIA RTX 5080 Laptop · NVIDIA RTX A4500 Laptop · NVIDIA RTX 5070 Ti Laptop · NVIDIA RTX 3500 Ada Laptop · NVIDIA RTX 5090 Laptop