General model by undi95 · 38.5B parameters
Everything this chip runs, machine by machine: MacBook Pro 14" M5 Pro, MacBook Pro 16" M5 Pro
Llamix2 MLewd 4x13B can run but will be tight at 72% of RAM. Consider a lower quantization or closing other apps.
— tok/s
Q2_K · 17.3 GB · Benchmark needed
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 | 43.4 GB | ~15 tok/s | ✗ |
| Q6_K | 33.8 GB | ~19 tok/s | ✗ |
| Q5_K_M | 29.2 GB | ~22 tok/s | ✗ |
| Q4_K_M | 25.4 GB | ~26 tok/s | ✗ |
| Q3_K_M | 21.5 GB | ~32 tok/s | ✗ |
| Q2_K Recommended | 17.3 GB | ~41 tok/s | ✓ |
Affiliate disclosure: the shop icons in this table are Amazon affiliate links. As an Amazon Associate, ModelPiper earns from qualifying purchases. Every fit rating, quantization and tok/s figure below is computed from the hardware specs and is not influenced by that.
Closest matches by use case and parameter count.
ToolPiper downloads, manages, and runs models with one click. Apple Silicon optimized.
Get ToolPiper free