General model by sapientinc · 1.18B parameters
Everything this chip runs, machine by machine: MacBook Pro 14" M5 Pro, MacBook Pro 16" M5 Pro
HRM Text 1B fits comfortably in your 24 GB Mac using Q8_0 quantization, using 8% of your RAM.
~136 tok/s
Q8_0 · 1.8 GB · Estimated
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 Recommended | 1.8 GB | ~136 tok/s | ✓ |
| Q6_K | 1.5 GB | ~179 tok/s | ✓ |
| Q5_K_M | 1.4 GB | ~210 tok/s | ✓ |
| Q4_K_M | 1.3 GB | ~247 tok/s | ✓ |
| Q3_K_M | 1.1 GB | ~298 tok/s | ✓ |
| Q2_K | 1.0 GB | ~387 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