Reasoning model by davidau · 24.94B parameters
Everything this chip runs, machine by machine: MacBook Pro 14" M5 Pro, MacBook Pro 16" M5 Pro
Llama3.1 MOE 4X8B Gated IQ Multi Tier Deep Reasoning 32B can run but will be tight at 80% of RAM. Consider a lower quantization or closing other apps.
— tok/s
Q5_K_M · 19.1 GB · Benchmark needed
Alternative: Q4_K_M (16.6 GB, ~12 tok/s)
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 | 28.3 GB | ~6 tok/s | ✗ |
| Q6_K | 22.1 GB | ~8 tok/s | ✗ |
| Q5_K_M Recommended | 19.1 GB | ~10 tok/s | ✓ |
| Q4_K_M | 16.6 GB | ~12 tok/s | ✓ |
| Q3_K_M | 14.1 GB | ~14 tok/s | ✓ |
| Q2_K | 11.4 GB | ~18 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