GPUs & Macs › NVIDIA RTX 5060
NVIDIA RTX 5060: local LLM speed
1 measured result for the NVIDIA RTX 5060.
Measured results
| Model | Generate tok/s | Prompt tok/s | Quant | Backend | Test | Source |
|---|---|---|---|---|---|---|
| Llama 3.2 1B Instruct | 185 | 7,818 | Q4_K_M | llamafile | LocalScore avg | LocalScore details |
What fits on the NVIDIA RTX 5060
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 |
|---|---|---|---|
| gemma-4-12B-it | IQ4_XS | 6.4 GB | 46.1 estimate |
| Qwen3.5-9B | Q5_K_S | 6.4 GB | 46.2 estimate |
| Qwen3.5-4B | Q8_0 | 4.5 GB | 65.6 estimate |
| MiMo-V2.6-Distill-Qwen-9B | Q4_K_M | 5.8 GB | 50.3 estimate |
| gemma-4-E4B-it | Q5_K_M | 5.5 GB | 53.6 estimate |
| Qwen3-4B | Q8_0 | 4.3 GB | 68.7 estimate |
| gemma-3-1b-it | Q8_0 | 1.1 GB | 245 estimate |
| gemma-4-E2B-it | Q8_0 | 5.0 GB | 59.2 estimate |
| DeepSeek-R1-0528-Qwen3-8B | Q5_K_M | 5.9 GB | 50.2 estimate |
| Llama-3.2-3B-Instruct | Q8_0 | 3.4 GB | 85.9 estimate |
| Phi-4-mini-instruct | Q8_0 | 4.1 GB | 72.0 estimate |
| gemma-3-4b-it | Q8_0 | 4.1 GB | 71.2 estimate |
| Qwen3-14B | UD-IQ3_XXS | 6.0 GB | 48.9 estimate |
| gemma-3-12b-it | Q3_K_M | 6.0 GB | 48.9 estimate |
Similar hardware
NVIDIA RTX 2070 SUPER · NVIDIA RTX 4060 Ti · NVIDIA RTX 2060 SUPER · NVIDIA GTX 1070 Ti · NVIDIA RTX 3060 Ti · NVIDIA RTX 3070 · NVIDIA GTX 1070 · NVIDIA RTX 3070 Ti