Chat model by yam-peleg · 10.48B parameters
Everything this chip runs, machine by machine: MacBook Pro 14" M5 Pro, MacBook Pro 16" M5 Pro
Hebrew Gemma 11B Instruct fits comfortably in your 24 GB Mac using Q8_0 quantization, using 51% of your RAM.
~15 tok/s
Q8_0 · 12.2 GB · Estimated
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 Recommended | 12.2 GB | ~15 tok/s | ✓ |
| Q6_K | 9.6 GB | ~20 tok/s | ✓ |
| Q5_K_M | 8.3 GB | ~24 tok/s | ✓ |
| Q4_K_M | 7.3 GB | ~28 tok/s | ✓ |
| Q3_K_M | 6.2 GB | ~34 tok/s | ✓ |
| Q2_K | 5.1 GB | ~44 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