Chat model by bytedance-seed · 36.15B parameters
Everything this chip runs, machine by machine: MacBook Pro 14" M5 Pro, MacBook Pro 16" M5 Pro
Seed OSS 36B Instruct can run but will be tight at 84% of RAM. Consider a lower quantization or closing other apps.
~10 tok/s
Q3_K_M · 20.2 GB · Estimated
Alternative: Q2_K (16.2 GB, ~13 tok/s)
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 | 40.8 GB | ~4 tok/s | ✗ |
| Q6_K | 31.8 GB | ~6 tok/s | ✗ |
| Q5_K_M | 27.5 GB | ~7 tok/s | ✗ |
| Q4_K_M | 23.8 GB | ~8 tok/s | ✗ |
| Q3_K_M Recommended | 20.2 GB | ~10 tok/s | ✓ |
| Q2_K | 16.2 GB | ~13 tok/s | ✓ |
GGUF Sources
Closest matches by use case and parameter count.
ToolPiper downloads, manages, and runs models with one click. Apple Silicon optimized.
Get ToolPiper — Free