General model by alea-institute · 3.69B parameters
Everything this chip runs, machine by machine: MacBook Pro 14" M5 Pro, MacBook Pro 16" M5 Pro
kl3m 003 3.7b fits comfortably in your 24 GB Mac using Q8_0 quantization, using 19% of your RAM.
Specifications
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 Recommended | 4.6 GB | ~152 tok/s | ✓ |
| Q6_K | 3.7 GB | ~199 tok/s | ✓ |
| Q5_K_M | 3.3 GB | ~234 tok/s | ✓ |
| Q4_K_M | 2.9 GB | ~274 tok/s | ✓ |
| Q3_K_M | 2.5 GB | ~331 tok/s | ✓ |
| Q2_K | 2.1 GB | ~430 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