Multimodal model by bytedance · 1.16B parameters
Everything this chip runs, machine by machine: MacBook Pro 14" M5 Pro, MacBook Pro 16" M5 Pro
Sa2VA 1B fits comfortably in your 24 GB Mac using Q8_0 quantization, using 7% of your RAM.
~139 tok/s
Q8_0 · 1.8 GB · Estimated
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 Recommended | 1.8 GB | ~139 tok/s | ✓ |
| Q6_K | 1.5 GB | ~182 tok/s | ✓ |
| Q5_K_M | 1.4 GB | ~214 tok/s | ✓ |
| Q4_K_M | 1.2 GB | ~251 tok/s | ✓ |
| Q3_K_M | 1.1 GB | ~303 tok/s | ✓ |
| Q2_K | 1.0 GB | ~393 tok/s | ✓ |
Affiliate disclosure: the shop icons in this table are Amazon affiliate links. As an Amazon Associate, ModelPiper earns from qualifying purchases. Every fit rating, quantization and tok/s figure below is computed from the hardware specs and is not influenced by that.
Closest matches by use case and parameter count.
ToolPiper downloads, manages, and runs models with one click. Apple Silicon optimized.
Get ToolPiper free