General model by Alibaba · 4.66B parameters · Released 2026-02-27
Qwen3.5 4B fits comfortably in your 24 GB Mac using Q8_0 quantization, using 24% of your RAM.
~35 tok/s
Q8_0 · 5.7 GB
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 Recommended | 5.7 GB | ~35 tok/s | ✓ |
| Q6_K | 4.5 GB | ~45 tok/s | ✓ |
| Q5_K_M | 4.0 GB | ~53 tok/s | ✓ |
| Q4_K_M | 3.5 GB | ~62 tok/s | ✓ |
| Q3_K_M | 3.0 GB | ~75 tok/s | ✓ |
| Q2_K | 2.5 GB | ~98 tok/s | ✓ |
GGUF Sources
ToolPiper downloads, manages, and runs models with one click. Apple Silicon optimized.
Get ToolPiper — Free