General model by osaurusai · 20.2B parameters
Everything this chip runs, machine by machine: MacBook Pro 14" M5 Pro, MacBook Pro 16" M5 Pro
DeepSeek V4 Flash JANGTQ2 fits comfortably in your 24 GB Mac using Q6_K quantization, using 75% of your RAM.
— tok/s
Q6_K · 18.0 GB · Benchmark needed
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 | 23.0 GB | ~110 tok/s | ✗ |
| Q6_K Recommended | 18.0 GB | ~145 tok/s | ✓ |
| Q5_K_M | 15.6 GB | ~170 tok/s | ✓ |
| Q4_K_M | 13.5 GB | ~199 tok/s | ✓ |
| Q3_K_M | 11.5 GB | ~241 tok/s | ✓ |
| Q2_K | 9.3 GB | ~313 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