General model by dnfs · 4.3B parameters
Everything this chip runs, machine by machine: MacBook Pro 14" M5 Pro, MacBook Pro 16" M5 Pro
gema 4b indra10k model1 fits comfortably in your 24 GB Mac using Q8_0 quantization, using 22% of your RAM.
~37 tok/s
Q8_0 · 5.3 GB · Estimated
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 Recommended | 5.3 GB | ~37 tok/s | ✓ |
| Q6_K | 4.2 GB | ~49 tok/s | ✓ |
| Q5_K_M | 3.7 GB | ~58 tok/s | ✓ |
| Q4_K_M | 3.3 GB | ~68 tok/s | ✓ |
| Q3_K_M | 2.8 GB | ~82 tok/s | ✓ |
| Q2_K | 2.4 GB | ~106 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