General model by beomi · 6.53B parameters
Everything this chip runs, machine by machine: MacBook Pro 14" M5 Pro, MacBook Pro 16" M5 Pro
KoRWKV 6B fits comfortably in your 24 GB Mac using Q8_0 quantization, using 32% of your RAM.
~25 tok/s
Q8_0 · 7.8 GB · Estimated
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 Recommended | 7.8 GB | ~25 tok/s | ✓ |
| Q6_K | 6.2 GB | ~32 tok/s | ✓ |
| Q5_K_M | 5.4 GB | ~38 tok/s | ✓ |
| Q4_K_M | 4.7 GB | ~45 tok/s | ✓ |
| Q3_K_M | 4.1 GB | ~54 tok/s | ✓ |
| Q2_K | 3.3 GB | ~70 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