GPUs & Macs › NVIDIA Quadro RTX 3000
NVIDIA Quadro RTX 3000: local LLM speed
1 measured result for the NVIDIA Quadro RTX 3000.
Measured results
| Model | Generate tok/s | Prompt tok/s | Quant | Backend | Test | Source |
|---|---|---|---|---|---|---|
| Llama 3.1 8B Instruct | 29.5 | 606 | Q4_K_M | llamafile | LocalScore avg | LocalScore details |
What fits on the NVIDIA Quadro RTX 3000
Estimates for this chip are scaled from a measured run: Llama 3.1 8B Instruct Q4_K_M at 29.5 tok/s (llamafile, source). Fit assumes the whole model in GPU memory with ~8K context.
| Model | Best quant that fits | File | Expected tok/s |
|---|---|---|---|
| gemma-4-12B-it | UD-IQ2_M | 4.2 GB | 34.4 estimate |
| Qwen3.5-9B | UD-IQ3_XXS | 4.0 GB | 36.1 estimate |
| Qwen3.5-4B | Q8_0 | 4.5 GB | 32.3 estimate |
| MiMo-V2.6-Distill-Qwen-9B | Q3_K_M | 4.5 GB | 32.4 estimate |
| gemma-4-E4B-it | Q3_K_M | 4.1 GB | 35.7 estimate |
| Qwen3-4B | Q8_0 | 4.3 GB | 33.9 estimate |
| gemma-3-1b-it | Q8_0 | 1.1 GB | 121 estimate |
| gemma-4-E2B-it | Q4_0 | 2.8 GB | 51.0 estimate |
| DeepSeek-R1-0528-Qwen3-8B | Q3_K_M | 4.1 GB | 35.2 estimate |
| Llama-3.2-3B-Instruct | Q8_0 | 3.4 GB | 42.4 estimate |
| Phi-4-mini-instruct | Q8_0 | 4.1 GB | 35.5 estimate |
| gemma-3-4b-it | Q8_0 | 4.1 GB | 35.1 estimate |
| Qwen3-14B | UD-IQ1_M | 4.1 GB | 35.7 estimate |
| gemma-3-12b-it | UD-IQ2_M | 4.4 GB | 33.2 estimate |
Similar hardware
NVIDIA GTX 1660 · NVIDIA GTX 1060 · NVIDIA RTX 2060 · NVIDIA GTX 1660 SUPER · NVIDIA P106-090 · NVIDIA GTX 1660 Ti · NVIDIA RTX 2070 SUPER · NVIDIA RTX 4060 Ti