General model by nvidia · 4.41B parameters
Everything this chip runs, machine by machine: MacBook Pro 14" M5 Pro, MacBook Pro 16" M5 Pro
Efficient DLM 4B fits comfortably in your 24 GB Mac using Q8_0 quantization, using 23% of your RAM.
~36 tok/s
Q8_0 · 5.4 GB · Estimated
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 Recommended | 5.4 GB | ~36 tok/s | ✓ |
| Q6_K | 4.3 GB | ~48 tok/s | ✓ |
| Q5_K_M | 3.8 GB | ~56 tok/s | ✓ |
| Q4_K_M | 3.3 GB | ~66 tok/s | ✓ |
| Q3_K_M | 2.9 GB | ~80 tok/s | ✓ |
| Q2_K | 2.4 GB | ~103 tok/s | ✓ |
Closest matches by use case and parameter count.
ToolPiper downloads, manages, and runs models with one click. Apple Silicon optimized.
Get ToolPiper — Free