General model by maziyarpanahi · 18.52B parameters
Everything this chip runs, machine by machine: MacBook Pro 14" M5 Pro, MacBook Pro 16" M5 Pro
Topxtral 4x7B v0.1 fits comfortably in your 24 GB Mac using Q6_K quantization, using 69% of your RAM.
— tok/s
Q6_K · 16.5 GB · Benchmark needed
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 | 21.2 GB | ~13 tok/s | ✗ |
| Q6_K Recommended | 16.5 GB | ~17 tok/s | ✓ |
| Q5_K_M | 14.3 GB | ~20 tok/s | ✓ |
| Q4_K_M | 12.5 GB | ~23 tok/s | ✓ |
| Q3_K_M | 10.6 GB | ~28 tok/s | ✓ |
| Q2_K | 8.6 GB | ~36 tok/s | ✓ |
GGUF Sources
Closest matches by use case and parameter count.
ToolPiper downloads, manages, and runs models with one click. Apple Silicon optimized.
Get ToolPiper — Free