General model by internlm · 6.28B parameters
Everything this chip runs, machine by machine: MacBook Pro 14" M5 Pro, MacBook Pro 16" M5 Pro
internlm2 7b fits comfortably in your 24 GB Mac using Q8_0 quantization, using 31% of your RAM.
~26 tok/s
Q8_0 · 7.5 GB · Estimated
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 Recommended | 7.5 GB | ~26 tok/s | ✓ |
| Q6_K | 5.9 GB | ~34 tok/s | ✓ |
| Q5_K_M | 5.2 GB | ~40 tok/s | ✓ |
| Q4_K_M | 4.6 GB | ~46 tok/s | ✓ |
| Q3_K_M | 3.9 GB | ~56 tok/s | ✓ |
| Q2_K | 3.2 GB | ~73 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