GPUs & Macs › NVIDIA P106-090
NVIDIA P106-090: local LLM speed
1 measured result for the NVIDIA P106-090.
Measured results
| Model | Generate tok/s | Prompt tok/s | Quant | Backend | Test | Source |
|---|---|---|---|---|---|---|
| Llama 3.2 1B Instruct | 39.2 | 923 | Q4_K_M | llamafile | LocalScore avg | LocalScore details |
What fits on the NVIDIA P106-090
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 | – estimate |
| Qwen3.5-9B | UD-IQ3_XXS | 4.0 GB | – estimate |
| Qwen3.5-4B | Q8_0 | 4.5 GB | – estimate |
| MiMo-V2.6-Distill-Qwen-9B | Q3_K_M | 4.5 GB | – estimate |
| gemma-4-E4B-it | Q3_K_M | 4.1 GB | – estimate |
| Qwen3-4B | Q8_0 | 4.3 GB | – estimate |
| gemma-3-1b-it | Q8_0 | 1.1 GB | – estimate |
| gemma-4-E2B-it | Q4_0 | 2.8 GB | – estimate |
| DeepSeek-R1-0528-Qwen3-8B | Q3_K_M | 4.1 GB | – estimate |
| Llama-3.2-3B-Instruct | Q8_0 | 3.4 GB | – estimate |
| Phi-4-mini-instruct | Q8_0 | 4.1 GB | – estimate |
| gemma-3-4b-it | Q8_0 | 4.1 GB | – estimate |
| Qwen3-14B | UD-IQ1_M | 4.1 GB | – estimate |
| gemma-3-12b-it | UD-IQ2_M | 4.4 GB | – estimate |
Similar hardware
NVIDIA GTX 1660 · NVIDIA GTX 1060 · NVIDIA RTX 2060 · NVIDIA Quadro RTX 3000 · NVIDIA GTX 1660 SUPER · NVIDIA GTX 1660 Ti · NVIDIA RTX 2070 SUPER · NVIDIA RTX 4060 Ti