General model by magistrtheone · 9.87B parameters
Everything this chip runs, machine by machine: MacBook Pro 14" M5 Pro, MacBook Pro 16" M5 Pro
veridian beta fits comfortably in your 24 GB Mac using Q8_0 quantization, using 48% of your RAM.
— tok/s
Q8_0 · 11.5 GB · Benchmark needed
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 Recommended | 11.5 GB | ~57 tok/s | ✓ |
| Q6_K | 9.0 GB | ~74 tok/s | ✓ |
| Q5_K_M | 7.9 GB | ~88 tok/s | ✓ |
| Q4_K_M | 6.9 GB | ~103 tok/s | ✓ |
| Q3_K_M | 5.9 GB | ~124 tok/s | ✓ |
| Q2_K | 4.8 GB | ~161 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