General model by llm-os-models · 5.05B parameters
Everything this chip runs, machine by machine: MacBook Pro 14" M5 Pro, MacBook Pro 16" M5 Pro
gemma 4 E2B Terminal SFT Native Liquid 1Epoch fits comfortably in your 24 GB Mac using Q8_0 quantization, using 26% of your RAM.
~32 tok/s
Q8_0 · 6.1 GB · Estimated
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 Recommended | 6.1 GB | ~32 tok/s | ✓ |
| Q6_K | 4.9 GB | ~42 tok/s | ✓ |
| Q5_K_M | 4.3 GB | ~49 tok/s | ✓ |
| Q4_K_M | 3.8 GB | ~58 tok/s | ✓ |
| Q3_K_M | 3.3 GB | ~70 tok/s | ✓ |
| Q2_K | 2.7 GB | ~90 tok/s | ✓ |
Closest matches by use case and parameter count.
ToolPiper downloads, manages, and runs models with one click. Apple Silicon optimized.
Get ToolPiper — Free