General model by loaiabdalslam · 0.49B parameters
Everything this chip runs, machine by machine: MacBook Pro 14" M5 Pro, MacBook Pro 16" M5 Pro
SLM FRIDGE ICED 0.5B 32BQWEN fits comfortably in your 24 GB Mac using Q8_0 quantization, using 4% of your RAM.
~328 tok/s
Q8_0 · 1.0 GB · Estimated
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 Recommended | 1.0 GB | ~328 tok/s | ✓ |
| Q6_K | 0.9 GB | ~431 tok/s | ✓ |
| Q5_K_M | 0.9 GB | ~507 tok/s | ✓ |
| Q4_K_M | 0.8 GB | ~594 tok/s | ✓ |
| Q3_K_M | 0.8 GB | ~718 tok/s | ✓ |
| Q2_K | 0.7 GB | ~931 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