General model by amd · 15.86B parameters
Everything this chip runs, machine by machine: MacBook Pro 14" M5 Pro, MacBook Pro 16" M5 Pro
Instella MoE 16B A3B Midtrain fits comfortably in your 24 GB Mac using Q8_0 quantization, using 76% of your RAM.
— tok/s
Q8_0 · 18.2 GB · Benchmark needed
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 Recommended | 18.2 GB | ~127 tok/s | ✓ |
| Q6_K | 14.2 GB | ~167 tok/s | ✓ |
| Q5_K_M | 12.3 GB | ~196 tok/s | ✓ |
| Q4_K_M | 10.7 GB | ~230 tok/s | ✓ |
| Q3_K_M | 9.2 GB | ~278 tok/s | ✓ |
| Q2_K | 7.4 GB | ~361 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