General model by osaurusai · 5.75B parameters
Everything this chip runs, machine by machine: MacBook Pro 14" M5 Pro, MacBook Pro 16" M5 Pro
Nemotron 3 Nano Omni 30B A3B JANGTQ4 fits comfortably in your 24 GB Mac using Q8_0 quantization, using 29% of your RAM.
— tok/s
Q8_0 · 6.9 GB · Benchmark needed
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 Recommended | 6.9 GB | ~296 tok/s | ✓ |
| Q6_K | 5.5 GB | ~388 tok/s | ✓ |
| Q5_K_M | 4.8 GB | ~457 tok/s | ✓ |
| Q4_K_M | 4.2 GB | ~536 tok/s | ✓ |
| Q3_K_M | 3.6 GB | ~647 tok/s | ✓ |
| Q2_K | 3.0 GB | ~840 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