General model by nvidia · 49.87B parameters
Llama 3_3 Nemotron Super 49B v1 requires 22.2 GB which exceeds your available memory. You need a Mac with more RAM.
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 | 56.1 GB | ~3 tok/s | ✗ |
| Q6_K | 43.7 GB | ~4 tok/s | ✗ |
| Q5_K_M | 37.7 GB | ~5 tok/s | ✗ |
| Q4_K_M | 32.7 GB | ~6 tok/s | ✗ |
| Q3_K_M | 27.7 GB | ~7 tok/s | ✗ |
| Q2_K | 22.2 GB | ~9 tok/s | ✗ |
GGUF Sources
ToolPiper downloads, manages, and runs models with one click. Apple Silicon optimized.
Get ToolPiper — Free