Chat model by davidau · 29.97B parameters
Everything this chip runs, machine by machine: MacBook Pro 14" M5 Pro, MacBook Pro 16" M5 Pro
Llama3.2 30B A3B II Dark Champion INSTRUCT Heretic Abliterated Uncensored can run but will be tight at 83% of RAM. Consider a lower quantization or closing other apps.
— tok/s
Q4_K_M · 19.8 GB · Benchmark needed
Alternative: Q3_K_M (16.8 GB, ~70 tok/s)
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 | 33.9 GB | ~32 tok/s | ✗ |
| Q6_K | 26.4 GB | ~42 tok/s | ✗ |
| Q5_K_M | 22.8 GB | ~49 tok/s | ✗ |
| Q4_K_M Recommended | 19.8 GB | ~58 tok/s | ✓ |
| Q3_K_M | 16.8 GB | ~70 tok/s | ✓ |
| Q2_K | 13.6 GB | ~90 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