General model by Alibaba · 2.27B parameters · Released 2026-02-28
Qwen3.5 2B fits comfortably in your 24 GB Mac using Q8_0 quantization, using 13% of your RAM.
~71 tok/s
Q8_0 · 3.0 GB
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 Recommended | 3.0 GB | ~71 tok/s | ✓ |
| Q6_K | 2.5 GB | ~93 tok/s | ✓ |
| Q5_K_M | 2.2 GB | ~109 tok/s | ✓ |
| Q4_K_M | 2.0 GB | ~128 tok/s | ✓ |
| Q3_K_M | 1.7 GB | ~155 tok/s | ✓ |
| Q2_K | 1.5 GB | ~201 tok/s | ✓ |
GGUF Sources
ToolPiper downloads, manages, and runs models with one click. Apple Silicon optimized.
Get ToolPiper — Free