GPUs & Macs › NVIDIA RTX A2000 12GB
NVIDIA RTX A2000 12GB: local LLM speed
3 measured results for the NVIDIA RTX A2000 12GB.
Measured results
| Model | Generate tok/s | Prompt tok/s | Quant | Backend | Test | Source |
|---|---|---|---|---|---|---|
| Llama 3.2 1B Instruct | 140 | 4,549 | Q4_K_M | llamafile | LocalScore avg | LocalScore details |
| Llama 3.1 8B Instruct | 35.7 | 976 | Q4_K_M | llamafile | LocalScore avg | LocalScore details |
| Qwen2.5 14B Instruct | 19.5 | 506 | Q4_K_M | llamafile | LocalScore avg | LocalScore details |
What fits on the NVIDIA RTX A2000 12GB
Estimates for this chip are scaled from a measured run: Llama 3.1 8B Instruct Q4_K_M at 35.7 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-IQ2_XXS | 7.3 GB | 24.2 estimate |
| gemma-4-12B-it | Q6_K | 9.8 GB | 18.0 estimate |
| Qwen3.5-9B | Q8_0 | 9.5 GB | 18.5 estimate |
| Qwen3.5-4B | Q8_0 | 4.5 GB | 39.2 estimate |
| gemma-4-26B-A4B-it | UD-IQ2_M | 10.0 GB | 57.1 estimate |
| MiMo-V2.6-Distill-Qwen-9B | Q8_0 | 9.5 GB | 18.4 estimate |
| gemma-4-E4B-it | Q8_0 | 8.2 GB | 21.5 estimate |
| Qwen3-4B | Q8_0 | 4.3 GB | 41.1 estimate |
| gemma-4-31B-it | UD-IQ2_XXS | 8.5 GB | 20.6 estimate |
| gemma-4-12B-it-qat-q4_0-unquantized | UD-Q4_K_XL | 6.7 GB | 26.2 estimate |
| gemma-3-1b-it | Q8_0 | 1.1 GB | 147 estimate |
| gemma-4-E2B-it | Q8_0 | 5.0 GB | 35.4 estimate |
| DeepSeek-R1-0528-Qwen3-8B | Q8_0 | 8.7 GB | 20.2 estimate |
| Llama-3.2-3B-Instruct | Q8_0 | 3.4 GB | 51.4 estimate |
Similar hardware
NVIDIA RTX A4000 · NVIDIA Quadro RTX 4000 · NVIDIA RTX 2000 Ada · NVIDIA RTX A2000 · NVIDIA Quadro P2000 · NVIDIA RTX A4500 · NVIDIA RTX 4000 Ada · NVIDIA T1000