General model by Alibaba · 27.78B parameters · Released 2026-02-24
Qwen3.5 27B can run but will be tight at 77% of RAM. Consider a lower quantization or closing other apps.
~10 tok/s
Q4_K_M · 18.4 GB
Alternative: Q3_K_M (15.7 GB, ~13 tok/s)
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 | 31.5 GB | ~6 tok/s | ✗ |
| Q6_K | 24.5 GB | ~8 tok/s | ✗ |
| Q5_K_M | 21.2 GB | ~9 tok/s | ✗ |
| Q4_K_M Recommended | 18.4 GB | ~10 tok/s | ✓ |
| Q3_K_M | 15.7 GB | ~13 tok/s | ✓ |
| Q2_K | 12.6 GB | ~16 tok/s | ✓ |
GGUF Sources
ToolPiper downloads, manages, and runs models with one click. Apple Silicon optimized.
Get ToolPiper — Free