Chat model by zai-org · 19.5B parameters
Everything this chip runs, machine by machine: MacBook Pro 14" M5 Pro, MacBook Pro 16" M5 Pro
cogvlm2 llama3 chat 19B fits comfortably in your 24 GB Mac using Q6_K quantization, using 72% of your RAM.
~11 tok/s
Q6_K · 17.4 GB · Estimated
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 | 22.3 GB | ~8 tok/s | ✗ |
| Q6_K Recommended | 17.4 GB | ~11 tok/s | ✓ |
| Q5_K_M | 15.0 GB | ~13 tok/s | ✓ |
| Q4_K_M | 13.1 GB | ~15 tok/s | ✓ |
| Q3_K_M | 11.1 GB | ~18 tok/s | ✓ |
| Q2_K | 9.0 GB | ~23 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