Chat model by DeepSeek · 1.98B parameters
deepseek vl 1.3b chat fits comfortably in your 24 GB Mac using Q8_0 quantization, using 11% of your RAM.
~81 tok/s
Q8_0 · 2.7 GB
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 Recommended | 2.7 GB | ~81 tok/s | ✓ |
| Q6_K | 2.2 GB | ~107 tok/s | ✓ |
| Q5_K_M | 2.0 GB | ~125 tok/s | ✓ |
| Q4_K_M | 1.8 GB | ~147 tok/s | ✓ |
| Q3_K_M | 1.6 GB | ~178 tok/s | ✓ |
| Q2_K | 1.4 GB | ~230 tok/s | ✓ |
ToolPiper downloads, manages, and runs models with one click. Apple Silicon optimized.
Get ToolPiper — Free