GPUs & Macs › NVIDIA TITAN RTX
NVIDIA TITAN RTX: local LLM speed
3 measured results for the NVIDIA TITAN RTX.
Measured results
| Model | Generate tok/s | Prompt tok/s | Quant | Backend | Test | Source |
|---|---|---|---|---|---|---|
| Llama 3.2 1B Instruct | 217 | 9,273 | Q4_K_M | llamafile | LocalScore avg | LocalScore details |
| Llama 3.1 8B Instruct | 71.2 | 2,226 | Q4_K_M | llamafile | LocalScore avg | LocalScore details |
| Qwen2.5 14B Instruct | 41.5 | 1,215 | Q4_K_M | llamafile | LocalScore avg · n=2 | LocalScore LocalScore details |
What fits on the NVIDIA TITAN RTX
Estimates for this chip are scaled from a measured run: Qwen2.5 14B Instruct Q4_K_M at 41.5 tok/s (llamafile, source). Fit assumes the whole model in GPU memory with ~8K context.
| Model | Best quant that fits | File | Expected tok/s |
|---|---|---|---|
| Qwen3.8-27B | UD-Q6_K | 22.0 GB | 17.0 estimate |
| gemma-4-12B-it | Q8_0 | 12.7 GB | 29.4 estimate |
| Qwen3.5-9B | Q8_0 | 9.5 GB | 39.1 estimate |
| Qwen3.5-4B | Q8_0 | 4.5 GB | 83.2 estimate |
| Qwen3.6-35B-A3B | UD-Q4_K_S | 20.9 GB | 104 estimate |
| gemma-4-26B-A4B-it | UD-Q5_K_M | 21.2 GB | 57.3 estimate |
| MiMo-V2.6-Distill-Qwen-9B | Q8_0 | 9.5 GB | 39.1 estimate |
| gemma-4-E4B-it | Q8_0 | 8.2 GB | 45.5 estimate |
| Muse-Glimmer-30B | UD-Q5_K_M | 19.2 GB | 19.4 estimate |
| Qwen3-4B | Q8_0 | 4.3 GB | 87.1 estimate |
| gemma-4-31B-it | Q5_K_M | 21.7 GB | 17.2 estimate |
| gemma-4-26B-A4B-it-qat-q4_0-unquantized | UD-Q4_K_XL | 14.2 GB | 85.1 estimate |
| gemma-4-12B-it-qat-q4_0-unquantized | UD-Q4_K_XL | 6.7 GB | 55.5 estimate |
| gemma-3-1b-it | Q8_0 | 1.1 GB | 311 estimate |
Similar hardware
NVIDIA RTX 4090 D · NVIDIA RTX 4090 · NVIDIA RTX 3090 Ti · NVIDIA RTX 3090 · NVIDIA Quadro P6000 · NVIDIA RTX 5090 · NVIDIA RTX 5080 · NVIDIA RTX 5070 Ti